Training in progress, step 63, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5767d4a161feb9a15983b4b61b4ea9f453f862fa51f16210deca4a28dcb867e8
+oid sha256:455817616b7f8783dd8c4d11736327262eedbdf402100d1d311a89854d653afc
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56ece74cebab974c23e9209f8e0a61c9586efe9554576cb7093f148fc9ca58a4
+oid sha256:2a6d7404395419f1c3a230c743a451f82b71c36dc848c9599c1a93aa9d45ea8d
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cea0571e03c42072c2619a6841806791c3454e943bf747e8a4e1158abf717848
+oid sha256:c2e69b2f578485f45062d20bf59fe081923730a7c50241733b3e57c77fb0b26c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f449418676ee143dc49fe68c0605204371c150076b291ef62a6b7b955efd8f73
+oid sha256:03b2d2818ab3151c9ed744a4cb682fe1730b800005846a54cc3da941ac8ce20d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9042386185243328,
+  "epoch": 1.0601779173207744,
   "eval_steps": 9,
-  "global_step": 54,
+  "global_step": 63,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -189,6 +189,35 @@
       "eval_samples_per_second": 2.786,
       "eval_steps_per_second": 1.393,
       "step": 54
+    },
+    {
+      "epoch": 0.9544740973312402,
+      "grad_norm": 7.194057941436768,
+      "learning_rate": 0.00011175373974578378,
+      "loss": 2.2831,
+      "step": 57
+    },
+    {
+      "epoch": 1.0099424385138671,
+      "grad_norm": 6.12868070602417,
+      "learning_rate": 0.0001,
+      "loss": 2.2803,
+      "step": 60
+    },
+    {
+      "epoch": 1.0601779173207744,
+      "grad_norm": 6.514719009399414,
+      "learning_rate": 8.824626025421626e-05,
+      "loss": 1.8185,
+      "step": 63
+    },
+    {
+      "epoch": 1.0601779173207744,
+      "eval_loss": 0.058350082486867905,
+      "eval_runtime": 73.106,
+      "eval_samples_per_second": 2.763,
+      "eval_steps_per_second": 1.382,
+      "step": 63
     }
   ],
   "logging_steps": 3,
@@ -208,7 +237,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.839916578949038e+17,
+  "total_flos": 3.313236008773878e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null