Training in progress, step 140, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99cfac1c2baddf1f9ea0d4faa7680daa5c2e80d219f5986eddd54fd836006122
+oid sha256:ab2e0910ee8ff17a681acdd56f9074e96fa82a916a8f3239bf3f1f3cd80ce465
 size 59827904

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a18d2c0a01d50a4c51715dadf4a0be0be51dc97452581044464ba783c996e19
+oid sha256:13e25365edc54422e82cbac4c671e2435e8bbd2900af3e9044725a0b51ab79a1
 size 30875540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:392da1c3f18aef86ac42978c5ab2b3ef58330aa9d54adc511669e79f01b39081
+oid sha256:f3620fd05065514f79fda6c0faf379ce93ec4350e71e2f2104721a44e9230ff6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fc750a6dfb3e5c9f642238b7443b0984a56e79b7c2731a6e152ecfc3e32f4e7
+oid sha256:671828e69cd8fd42106344a5797cbc78f701a434a6386d9dfacd16451ba179aa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.06601870529983496,
+  "epoch": 0.06846384253316218,
   "eval_steps": 34,
-  "global_step": 135,
+  "global_step": 140,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -984,6 +984,49 @@
       "learning_rate": 6.387583338128471e-05,
       "loss": 9.7205,
       "step": 135
+    },
+    {
+      "epoch": 0.0665077327465004,
+      "grad_norm": 9.914893519909028e+17,
+      "learning_rate": 6.215889499576898e-05,
+      "loss": 8.1576,
+      "step": 136
+    },
+    {
+      "epoch": 0.0665077327465004,
+      "eval_loss": 9.333438873291016,
+      "eval_runtime": 880.1222,
+      "eval_samples_per_second": 2.935,
+      "eval_steps_per_second": 0.978,
+      "step": 136
+    },
+    {
+      "epoch": 0.06699676019316585,
+      "grad_norm": Infinity,
+      "learning_rate": 6.0454879312945754e-05,
+      "loss": 9.5434,
+      "step": 137
+    },
+    {
+      "epoch": 0.06748578763983129,
+      "grad_norm": Infinity,
+      "learning_rate": 5.876436825260967e-05,
+      "loss": 9.9258,
+      "step": 138
+    },
+    {
+      "epoch": 0.06797481508649673,
+      "grad_norm": Infinity,
+      "learning_rate": 5.708793912273911e-05,
+      "loss": 8.8349,
+      "step": 139
+    },
+    {
+      "epoch": 0.06846384253316218,
+      "grad_norm": Infinity,
+      "learning_rate": 5.542616442234618e-05,
+      "loss": 10.4222,
+      "step": 140
     }
   ],
   "logging_steps": 1,
@@ -1003,7 +1046,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.976047562542285e+17,
+  "total_flos": 3.086271546340147e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null