Training in progress, step 143, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c25138bad319d0c4c5729b1b2847d0a2e2c73a87f4ff6b0b44feb716aa4c3a8f
+oid sha256:1685ede40bf022895c16fdd979d8441ad50f25d8a257e5bdc89189c167dab1c3
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2691cfe587c2386184fe60bd924e63496f82a3568d470a15f8f6b2aa87d5bf3d
+oid sha256:275a46bdf722787b2aa4bf4d5b996d0a53af3e3e0a682f890bc4c8fb30eb8213
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae02f105e3120f5249e0cc5f5ee89c3c7189b19796356620717a201b623d87a1
+oid sha256:b5cfad76a3456e3da824d7fc27ce2b7f891ca9d74102cfe39e4e466ffaf61ef4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f9bc32841f0c3d8bc8ea90b0bc3413eece3c955acd985fe2913112493248454
+oid sha256:a71f60f9bd2ac4332e4682c06bcf0e8b6f23e0f17b0fa94d84f1fe3045e8b4a8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03600110772639158,
+  "epoch": 0.03960121849903074,
   "eval_steps": 13,
-  "global_step": 130,
+  "global_step": 143,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -396,6 +396,42 @@
       "eval_samples_per_second": 13.198,
       "eval_steps_per_second": 1.651,
       "step": 130
+    },
+    {
+      "epoch": 0.03655497092218222,
+      "grad_norm": 2.236476421356201,
+      "learning_rate": 4.023611372427471e-06,
+      "loss": 1.3822,
+      "step": 132
+    },
+    {
+      "epoch": 0.03738576571586818,
+      "grad_norm": 2.308274507522583,
+      "learning_rate": 2.8058334845816213e-06,
+      "loss": 1.3381,
+      "step": 135
+    },
+    {
+      "epoch": 0.03821656050955414,
+      "grad_norm": 1.7674018144607544,
+      "learning_rate": 1.8018569652073381e-06,
+      "loss": 1.396,
+      "step": 138
+    },
+    {
+      "epoch": 0.0390473553032401,
+      "grad_norm": 2.1131505966186523,
+      "learning_rate": 1.016230078838226e-06,
+      "loss": 1.3624,
+      "step": 141
+    },
+    {
+      "epoch": 0.03960121849903074,
+      "eval_loss": 0.3427909314632416,
+      "eval_runtime": 460.8668,
+      "eval_samples_per_second": 13.197,
+      "eval_steps_per_second": 1.651,
+      "step": 143
     }
   ],
   "logging_steps": 3,
@@ -415,7 +451,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.0955308444614656e+17,
+  "total_flos": 2.2917789711649997e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null