Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9e74c4e9fbb9ffaa9c42beaa47578415c5068468ca458abbff3b85dcaef396a
+oid sha256:0d83d6b0dea4d7afdd1b0c1435fc0d8d0efd0c816595a37f3a27f2ba63092b92
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a6c3ad45446324aea45b850b07656ecb0b94892deaf37d236bb0de61f98013c
+oid sha256:f2ae8c4890c71341784c087e5720a15ac6806d3a9e5bc181c79348d517a22aee
 size 243802484

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c757d7b5369cfc819bbd3a5531b5642872e54fa92b5658296e84ac7602cf90ca
+oid sha256:0240ec5c8e5d2c629daf096f222fc64d00047316e0a1e414493431e3632a128e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8ce05761f46e7cf72fb17a02e3a0ca15c9d25ce3babf590eeb40568923b8bac
+oid sha256:d2d754412c61116546142914503e7369d0cc35d3c380a07e5218f595d76b6d96
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.974004864692688,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.09195402298850575,
+  "best_metric": 0.9704466462135315,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.12260536398467432,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -389,6 +389,126 @@
       "eval_samples_per_second": 19.702,
       "eval_steps_per_second": 4.927,
       "step": 150
+    },
+    {
+      "epoch": 0.09379310344827586,
+      "grad_norm": 0.21658183634281158,
+      "learning_rate": 1.435357758543015e-05,
+      "loss": 0.895,
+      "step": 153
+    },
+    {
+      "epoch": 0.09563218390804598,
+      "grad_norm": 0.20556800067424774,
+      "learning_rate": 1.2658926150792322e-05,
+      "loss": 1.079,
+      "step": 156
+    },
+    {
+      "epoch": 0.09747126436781609,
+      "grad_norm": 0.207136869430542,
+      "learning_rate": 1.1056136061894384e-05,
+      "loss": 1.0331,
+      "step": 159
+    },
+    {
+      "epoch": 0.0993103448275862,
+      "grad_norm": 0.21127332746982574,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.9742,
+      "step": 162
+    },
+    {
+      "epoch": 0.10114942528735632,
+      "grad_norm": 0.20534484088420868,
+      "learning_rate": 8.141676086873572e-06,
+      "loss": 0.8345,
+      "step": 165
+    },
+    {
+      "epoch": 0.10298850574712644,
+      "grad_norm": 0.22418928146362305,
+      "learning_rate": 6.837175952121306e-06,
+      "loss": 0.8135,
+      "step": 168
+    },
+    {
+      "epoch": 0.10482758620689656,
+      "grad_norm": 0.2613643407821655,
+      "learning_rate": 5.6388590278194096e-06,
+      "loss": 0.8241,
+      "step": 171
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 0.2851332426071167,
+      "learning_rate": 4.549673247541875e-06,
+      "loss": 0.8675,
+      "step": 174
+    },
+    {
+      "epoch": 0.10850574712643678,
+      "grad_norm": 0.4742611348628998,
+      "learning_rate": 3.5722980755146517e-06,
+      "loss": 0.7109,
+      "step": 177
+    },
+    {
+      "epoch": 0.1103448275862069,
+      "grad_norm": 0.38285398483276367,
+      "learning_rate": 2.7091379149682685e-06,
+      "loss": 0.3901,
+      "step": 180
+    },
+    {
+      "epoch": 0.11218390804597701,
+      "grad_norm": 0.5817790031433105,
+      "learning_rate": 1.962316193157593e-06,
+      "loss": 0.7918,
+      "step": 183
+    },
+    {
+      "epoch": 0.11402298850574713,
+      "grad_norm": 1.3340506553649902,
+      "learning_rate": 1.333670137599713e-06,
+      "loss": 1.2167,
+      "step": 186
+    },
+    {
+      "epoch": 0.11586206896551725,
+      "grad_norm": 1.6385730504989624,
+      "learning_rate": 8.247462563808817e-07,
+      "loss": 1.26,
+      "step": 189
+    },
+    {
+      "epoch": 0.11770114942528735,
+      "grad_norm": 1.7007404565811157,
+      "learning_rate": 4.367965336512403e-07,
+      "loss": 1.1193,
+      "step": 192
+    },
+    {
+      "epoch": 0.11954022988505747,
+      "grad_norm": 1.5352810621261597,
+      "learning_rate": 1.7077534966650766e-07,
+      "loss": 1.2129,
+      "step": 195
+    },
+    {
+      "epoch": 0.12137931034482759,
+      "grad_norm": 1.307135820388794,
+      "learning_rate": 2.7337132953697554e-08,
+      "loss": 1.0943,
+      "step": 198
+    },
+    {
+      "epoch": 0.12260536398467432,
+      "eval_loss": 0.9704466462135315,
+      "eval_runtime": 139.5388,
+      "eval_samples_per_second": 19.686,
+      "eval_steps_per_second": 4.923,
+      "step": 200
     }
   ],
   "logging_steps": 3,
@@ -412,12 +532,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 9.119562048366182e+16,
+  "total_flos": 1.2164158426447872e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null