Training in progress, epoch 1, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41edb5256aa421ac63d1b2ba4f20a4d47257d2b4a65a5d4b1232ae71729f5362
+oid sha256:af136286df6ff5905af165343cf57f5a831518e937bb6fc0471b78269e350229
 size 48552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3acf8603b1c1cef0dd78862911a72d620d40796a965c4e19dd553291458f210
+oid sha256:be91a147d44e75d2fcfd702628b092ecfc4ce8e1dd0ac3f0bd83e38b571d6119
 size 107046

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3aa86072d894b06ed15a781ebf27303cfbb0a54143c21949f75c3251dd2ec55c
+oid sha256:b97e51ea9f5d34aebc6d066d7c2fb7a20dbec78f27d117049f04bf79c02536c3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7962e06291987b3327e85ffe1a0f48aec5a6651b8b5139bec8a1fd5526407429
+oid sha256:a277d82c7576fb11769cdddd31bacd8b5bc730226a0e626981ae85a7a41efa44
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9979035639412998,
+  "epoch": 1.9958071278825997,
   "eval_steps": 500,
-  "global_step": 119,
+  "global_step": 238,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -50,6 +50,56 @@
       "eval_samples_per_second": 242.468,
       "eval_steps_per_second": 62.417,
       "step": 119
+    },
+    {
+      "epoch": 1.0062893081761006,
+      "grad_norm": 0.11942638456821442,
+      "learning_rate": 0.00012713675213675213,
+      "loss": 12.3702,
+      "step": 120
+    },
+    {
+      "epoch": 1.1740041928721174,
+      "grad_norm": 0.059040140360593796,
+      "learning_rate": 0.00010576923076923077,
+      "loss": 11.8371,
+      "step": 140
+    },
+    {
+      "epoch": 1.3417190775681342,
+      "grad_norm": 0.06853944063186646,
+      "learning_rate": 8.440170940170941e-05,
+      "loss": 12.0029,
+      "step": 160
+    },
+    {
+      "epoch": 1.509433962264151,
+      "grad_norm": 0.030212825164198875,
+      "learning_rate": 6.303418803418804e-05,
+      "loss": 11.9184,
+      "step": 180
+    },
+    {
+      "epoch": 1.6771488469601676,
+      "grad_norm": 0.034588687121868134,
+      "learning_rate": 4.1666666666666665e-05,
+      "loss": 11.9407,
+      "step": 200
+    },
+    {
+      "epoch": 1.8448637316561844,
+      "grad_norm": 0.0361829474568367,
+      "learning_rate": 2.02991452991453e-05,
+      "loss": 11.8561,
+      "step": 220
+    },
+    {
+      "epoch": 1.9958071278825997,
+      "eval_loss": 11.917513847351074,
+      "eval_runtime": 0.4181,
+      "eval_samples_per_second": 241.592,
+      "eval_steps_per_second": 62.192,
+      "step": 238
     }
   ],
   "logging_steps": 20,
@@ -69,7 +119,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 134180413440.0,
+  "total_flos": 268360826880.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null