Model save

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,62 @@
+---
+tags:
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- generator
+model-index:
+- name: zephyr-2b-gemma-dft-debug
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# zephyr-2b-gemma-dft-debug
+
+This model was trained from scratch on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2957.4309
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 2978.2934     | 0.9982 | 270  | 2957.4309       |
+
+
+### Framework versions
+
+- Transformers 4.43.3
+- Pytorch 2.3.1+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9981515711645101,
+    "total_flos": 5.260333472022528e+16,
+    "train_loss": 3746.6009367766205,
+    "train_runtime": 2500.0335,
+    "train_samples": 6750,
+    "train_samples_per_second": 3.461,
+    "train_steps_per_second": 0.108
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "data/gemma-2b",
+  "architectures": [
+    "GemmaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "head_dim": 256,
+  "hidden_act": "gelu",
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 16384,
+  "max_position_embeddings": 8192,
+  "model_type": "gemma",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 18,
+  "num_key_value_heads": 1,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.43.3",
+  "use_cache": false,
+  "vocab_size": 256000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.43.3"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:673f21f6511aa4d6965bb497bbc307de1fecdcdb64045e3d677f47944e65fa5a
+size 4945242264

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b8d5752b1fa47fe467d63499fa2ea4087cf9ace96733181c06492817e07a1f7
+size 67121608

model.safetensors.index.json

@@ -0,0 +1,171 @@
+{
+  "metadata": {
+    "total_size": 5012344832
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

runs/Aug01_08-13-23_ale-distillm-8-0-0/events.out.tfevents.1722496416.ale-distillm-8-0-0.150135.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1b21cdd4d55dd68cfa415502ad9e43df20cb1f421d9e10311bc60cc3e568eb7
+size 5801

runs/Aug01_08-19-49_ale-distillm-8-0-0/events.out.tfevents.1722496802.ale-distillm-8-0-0.150944.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a991f1dfcaf80b984ee9f5682235fef8c8046ea2216af91d4aa3dcc6d5f1124
+size 5801

runs/Aug01_08-23-09_ale-distillm-8-0-0/events.out.tfevents.1722497020.ale-distillm-8-0-0.151618.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:775f30c0c4c1ac6f5300c0c214e81e3b3560c8d75da600a2ce715cb699ef3b17
+size 5180

runs/Aug01_08-43-38_ale-distillm-8-0-0/events.out.tfevents.1722498230.ale-distillm-8-0-0.155112.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c46f3350073f6cbb8dca2704e1fb48412e88e9adcb64c41193b3406aa68557a4
+size 5180

runs/Aug01_08-50-20_ale-distillm-8-0-0/events.out.tfevents.1722498632.ale-distillm-8-0-0.155311.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee34231a8d43aff5288de9719c8097ccbf96600eeab75c1881281e7d5964184e
+size 5180

runs/Aug01_08-51-49_ale-distillm-8-0-0/events.out.tfevents.1722498721.ale-distillm-8-0-0.155510.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bd7d4392525199c21c57688fdb450a139382247d2059f1686302c536532d98d
+size 6008

runs/Aug01_08-57-31_ale-distillm-8-0-0/events.out.tfevents.1722499073.ale-distillm-8-0-0.156427.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3421344c3c805aa705d7c21ed8e5b8c8cdcc521987a1b4a8aeac0681aa1fb3e
+size 5180

runs/Aug01_10-28-04_ale-distillm-8-0-0/events.out.tfevents.1722504496.ale-distillm-8-0-0.158148.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:570b9947f2c8485235fa2eb477461dad72c6272e4273b55afceb55afc428b21f
+size 5180

runs/Aug01_10-37-23_ale-distillm-8-0-0/events.out.tfevents.1722505055.ale-distillm-8-0-0.158347.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31c7bd0695f11af4ba2ea2b717f9226ac2a0708c4985767a6ed79896cafbcc77
+size 5387

runs/Aug01_10-40-13_ale-distillm-8-0-0/events.out.tfevents.1722505225.ale-distillm-8-0-0.158858.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1c6a83095901a7e40018b745aa8fc6f069f431615dc7e7269d716b27a077a6a
+size 7250

runs/Aug01_11-08-21_ale-distillm-8-0-0/events.out.tfevents.1722506913.ale-distillm-8-0-0.165077.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b62e11a461dfd9a2958947d0a733728c4e44cac8042d01b420fe0a27b63024c
+size 7250

runs/Aug01_11-18-26_ale-distillm-8-0-0/events.out.tfevents.1722507521.ale-distillm-8-0-0.166956.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9851a828a33ffaf5843a42c2d07312f096d21ddbf5e40dc938a35874a4ecdce3
+size 5387

runs/Aug01_11-55-49_ale-distillm-8-0-0/events.out.tfevents.1722509761.ale-distillm-8-0-0.167857.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:083938771864a047148f66da3ae73f1acad7a45f81760f1f4afb83d99a769beb
+size 5801

runs/Aug01_11-59-21_ale-distillm-8-0-0/events.out.tfevents.1722509973.ale-distillm-8-0-0.168664.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc45f5f5e6a02580796a5b351860408570c047e8bbd1225b03ace29a37a83a8c
+size 5594

runs/Aug01_12-11-31_ale-distillm-8-0-0/events.out.tfevents.1722510703.ale-distillm-8-0-0.169234.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c34fe08825a30697bab13b6a4d47be84a730ee4d2f2129d167e8e0a1d0cd1bc9
+size 5387

runs/Aug01_12-15-56_ale-distillm-8-0-0/events.out.tfevents.1722510981.ale-distillm-8-0-0.169880.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9011fe468442bbd47dbf08db5d4a2444bff31c1f04a393521acb2d183dd9a80b
+size 5180

runs/Aug01_12-45-33_ale-distillm-8-0-0/events.out.tfevents.1722512949.ale-distillm-8-0-0.172568.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d463a3a08a22d2214bb763be5fc06aa26c1c9783755e2a9aab6bab633f35b182
+size 5180

runs/Aug01_12-57-42_ale-distillm-8-0-0/events.out.tfevents.1722513474.ale-distillm-8-0-0.174648.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b53ffdee6aec5ac4f86c1cab71d5a4d7983b6cac2676ac0c4e8a045aeb890d3
+size 7457

runs/Aug01_13-06-02_ale-distillm-8-0-0/events.out.tfevents.1722513974.ale-distillm-8-0-0.176733.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdab057e1f0f37f5775610a57e5d3f99c5ee7b6a850c490006b70f872d77b7d6
+size 8906

runs/Aug01_13-19-22_ale-distillm-8-0-0/events.out.tfevents.1722514774.ale-distillm-8-0-0.179826.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa29afbf9ae47268905683a16d6ea3bfb42326af1404807e836285cbee93307a
+size 17099

runs/Aug01_14-32-12_ale-distillm-8-0-0/events.out.tfevents.1722519239.ale-distillm-8-0-0.189662.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98e10f45e6c730a87860d507ca9c5428a28577a2b0cd5f89966f90dc889097a3
+size 5180

runs/Aug01_15-40-54_ale-distillm-8-0-0/events.out.tfevents.1722523316.ale-distillm-8-0-0.190122.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d90361df317feaa69353a091006c324614ec2a802efbb818693406141b80d15
+size 5180

runs/Aug01_16-19-27_ale-distillm-8-0-0/events.out.tfevents.1722525579.ale-distillm-8-0-0.190777.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:959e6f64280ee78c16e4516a0f932366000c51266e277adb641a24edf0a24542
+size 17099

runs/Jul24_15-15-56_ale-distillm-8-0-0/events.out.tfevents.1721830680.ale-distillm-8-0-0.1471.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:966f2e545e0ed76fbdc9b9d47c1b3bbde6432052c7f7e552eec8c1cb5dcb14fc
+size 5180

runs/Jul24_15-22-07_ale-distillm-8-0-0/events.out.tfevents.1721830970.ale-distillm-8-0-0.2114.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54f666a2711fcedc5dd27a57a32290ed14ab4229d2d6ba70c357fc027fabe86c
+size 5180

runs/Jul24_15-28-05_ale-distillm-8-0-0/events.out.tfevents.1721831314.ale-distillm-8-0-0.3143.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fd46aaee1504e368e5490dd9e61567fb04d26016e4e53dce0fc78be2dc9a218
+size 5180

runs/Jul25_09-25-47_ale-distillm-8-0-0/events.out.tfevents.1721895984.ale-distillm-8-0-0.16592.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:900c848a3363f4cdc17cd2a28a0c9be4595a47cfbafefffe4f02d718e1d4645f
+size 5180

runs/Jul25_14-53-34_ale-distillm-8-0-0/events.out.tfevents.1721915707.ale-distillm-8-0-0.28984.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27ce9fefcf320cef6bf74593a9ad816a27d309e3657470304c7f6759956c4c68
+size 5594

runs/Jul25_16-32-18_ale-distillm-8-0-0/events.out.tfevents.1721921563.ale-distillm-8-0-0.29850.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9529257f55422b3a834eb32912332de4bd7b6f13d9f93fffa5a7d4c0f0063a18
+size 5180

runs/Jul25_17-32-25_ale-distillm-8-0-0/events.out.tfevents.1721925178.ale-distillm-8-0-0.30782.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a06f62cd84736eadf6aaecc96166d0d4d1bc24b8bfefc70294a76e8d0d3d390
+size 5180

runs/Jul25_17-39-32_ale-distillm-8-0-0/events.out.tfevents.1721925610.ale-distillm-8-0-0.31222.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22f8cb7ef8f864ca40c3a2b788d149bd1f299a83b81a6d55e15f09076300a087
+size 5180

runs/Jul25_17-52-25_ale-distillm-8-0-0/events.out.tfevents.1721926378.ale-distillm-8-0-0.32561.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d21dbb13ce056a50ca4ea17be5f72c25a4ad1d8aedab350244ca1e559f8c627
+size 5180

runs/Jul25_18-09-33_ale-distillm-8-0-0/events.out.tfevents.1721927396.ale-distillm-8-0-0.34375.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82da5f2f40568f733299257ccd2d61a8dd008c8d1599060d7abf3fb9c5f7a67f
+size 5180

runs/Jul26_09-07-00_ale-distillm-8-0-0/events.out.tfevents.1721981241.ale-distillm-8-0-0.37979.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ade46f78113518d29f16a04bd8c0af98e65dea3042522869b9b270ffa2353d18
+size 5180

runs/Jul26_09-46-13_ale-distillm-8-0-0/events.out.tfevents.1721983603.ale-distillm-8-0-0.41839.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4003a0c8d70f0ee539df81cadb7eb4a9031d77d23a7c191c84843244d1986d1a
+size 5180

runs/Jul26_09-48-57_ale-distillm-8-0-0/events.out.tfevents.1721983776.ale-distillm-8-0-0.42185.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:499e34cef3c0389706938d6bbe091aa6cad4e6257cd8c341b2646a2ab5c4dc7d
+size 5180

runs/Jul26_09-55-11_ale-distillm-8-0-0/events.out.tfevents.1721984142.ale-distillm-8-0-0.42830.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a293268a3a33410f3dc98ca69f6f2837c08cfa95b72dfd136fda61b6f833b3d2
+size 5180

runs/Jul26_10-11-22_ale-distillm-8-0-0/events.out.tfevents.1721985387.ale-distillm-8-0-0.44021.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c4772baeb03eedcf4f36814f85fb5b4c656782cc5cb4aa901fe8533df400118
+size 5180

runs/Jul26_10-30-54_ale-distillm-8-0-0/events.out.tfevents.1721986269.ale-distillm-8-0-0.46148.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78df162956e38c5d80368b7b263d2315389eb2f19f9dd29967beb90b7a6623ec
+size 5180

runs/Jul26_10-34-46_ale-distillm-8-0-0/events.out.tfevents.1721986500.ale-distillm-8-0-0.46693.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce7b815838cb3359c3116a7ce9faa68e37d1d0944fd2806b6b01d0149d0c9497
+size 5180

runs/Jul26_10-50-00_ale-distillm-8-0-0/events.out.tfevents.1721987414.ale-distillm-8-0-0.47867.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10a8667472f2787fe03b5643ff93967c42377088f8243b356f7fa18e621fd054
+size 7043

runs/Jul31_17-04-25_ale-distillm-8-0-0/events.out.tfevents.1722441943.ale-distillm-8-0-0.139252.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27a526ad1b8807a242af99b41aad18c43856a96e8c17a1d99f421503ad7dc216
+size 5180