Upload with huggingface_hub

config.json

@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "JackFram/llama-160m",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.28.0.dev0"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0883475aed864c126708ba0d05deca1082e0db3cd5f2f12b6a0aac2ee44e0a6b
+size 1299404037

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a18cbb1baf34ffd0b0dcb009783090f8862c563c7ec506be175a953544498cff
+size 649710859

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:250b39995be75e0031804576c70e5a910b854c31b6e2a1b1c7f64503fef23c2d
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91311d098b4256bd12114d4be30ae2b2c10c2b115dbfc2ae24d747d88f7a407b
+size 623

trainer_state.json

@@ -0,0 +1,114 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.999466666666667,
+  "global_step": 3281,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00027499999999999996,
+      "loss": 2.2976,
+      "step": 468
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.336582899093628,
+      "eval_runtime": 78.6661,
+      "eval_samples_per_second": 474.805,
+      "eval_steps_per_second": 59.352,
+      "step": 468
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0002499465811965812,
+      "loss": 1.9877,
+      "step": 937
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2.378277540206909,
+      "eval_runtime": 78.6809,
+      "eval_samples_per_second": 474.715,
+      "eval_steps_per_second": 59.341,
+      "step": 937
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.00022489316239316236,
+      "loss": 1.7492,
+      "step": 1406
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 2.487154960632324,
+      "eval_runtime": 79.1756,
+      "eval_samples_per_second": 471.749,
+      "eval_steps_per_second": 58.97,
+      "step": 1406
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.00019983974358974357,
+      "loss": 1.5071,
+      "step": 1875
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 2.652348041534424,
+      "eval_runtime": 79.1787,
+      "eval_samples_per_second": 471.73,
+      "eval_steps_per_second": 58.968,
+      "step": 1875
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.00017483974358974358,
+      "loss": 1.2629,
+      "step": 2343
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 2.86438250541687,
+      "eval_runtime": 79.0436,
+      "eval_samples_per_second": 472.537,
+      "eval_steps_per_second": 59.069,
+      "step": 2343
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 0.00014978632478632477,
+      "loss": 1.0163,
+      "step": 2812
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 3.113752603530884,
+      "eval_runtime": 78.7145,
+      "eval_samples_per_second": 474.512,
+      "eval_steps_per_second": 59.316,
+      "step": 2812
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 0.00012473290598290598,
+      "loss": 0.7859,
+      "step": 3281
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 3.4060871601104736,
+      "eval_runtime": 78.8544,
+      "eval_samples_per_second": 473.671,
+      "eval_steps_per_second": 59.21,
+      "step": 3281
+    }
+  ],
+  "max_steps": 5616,
+  "num_train_epochs": 12,
+  "total_flos": 1.2915021003952435e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47cb890789ac3d7cff1bbdb21d08c36d24fb1165f2fea690bbdba072268a5de9
+size 3567