Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:296c0e7114323a9858809edd080f8475c9209749e39f10eaafa92445d05bf713
+oid sha256:2b526ca670ef11b578825ede220a8c2ee374498184c93dfa6f812ff05a0045aa
 size 14696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:487b5b471a84ceaf03d95b191de81bbc11c9b64710902f665b0ea7368d7d502c
+oid sha256:c34037f096fdcb6b5071ea34a28a11df1248f537dfd09aba8d5ef214afc541c5
 size 39398

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48d41985628b63b1f03308534e42f5f4fade1dc9f1a7ca147144af3b829d1153
+oid sha256:3a2809375c44051deea8394ef4e524b537561ea599f6f054cbc21229ed9516f2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccc7e73cc5879da996ace4c3a10d9efe08a100111973e801d61997747e95e982
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.14233576642335766,
+  "epoch": 0.18248175182481752,
   "eval_steps": 13,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -312,6 +312,83 @@
       "eval_samples_per_second": 251.13,
       "eval_steps_per_second": 125.565,
       "step": 39
+    },
+    {
+      "epoch": 0.145985401459854,
+      "grad_norm": 0.010320533998310566,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 11.9364,
+      "step": 40
+    },
+    {
+      "epoch": 0.14963503649635038,
+      "grad_norm": 0.015699736773967743,
+      "learning_rate": 2.3959403439996907e-05,
+      "loss": 11.9369,
+      "step": 41
+    },
+    {
+      "epoch": 0.15328467153284672,
+      "grad_norm": 0.015644729137420654,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 11.9351,
+      "step": 42
+    },
+    {
+      "epoch": 0.15693430656934307,
+      "grad_norm": 0.016171997413039207,
+      "learning_rate": 1.4735983564590783e-05,
+      "loss": 11.9347,
+      "step": 43
+    },
+    {
+      "epoch": 0.16058394160583941,
+      "grad_norm": 0.01559949479997158,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 11.9351,
+      "step": 44
+    },
+    {
+      "epoch": 0.16423357664233576,
+      "grad_norm": 0.010892484337091446,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 11.939,
+      "step": 45
+    },
+    {
+      "epoch": 0.1678832116788321,
+      "grad_norm": 0.012285547330975533,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 11.9399,
+      "step": 46
+    },
+    {
+      "epoch": 0.17153284671532848,
+      "grad_norm": 0.011205232702195644,
+      "learning_rate": 2.7630079602323442e-06,
+      "loss": 11.9356,
+      "step": 47
+    },
+    {
+      "epoch": 0.17518248175182483,
+      "grad_norm": 0.011147280223667622,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 11.9377,
+      "step": 48
+    },
+    {
+      "epoch": 0.17883211678832117,
+      "grad_norm": 0.012826742604374886,
+      "learning_rate": 3.0826662668720364e-07,
+      "loss": 11.9364,
+      "step": 49
+    },
+    {
+      "epoch": 0.18248175182481752,
+      "grad_norm": 0.01375089306384325,
+      "learning_rate": 0.0,
+      "loss": 11.9352,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -326,12 +403,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4608294912.0,
+  "total_flos": 5908070400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null