Training in progress, step 135, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04219c720b69da395b407d47b273d1b6f06d909e0e16bc792d9da19239623894
+oid sha256:2693e3c807ab1261a91352b2a34141c7debf3c87e07888e0213731c63bf1238c
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5045a1eecb46de53b6cd1195ec2d1add713e18b2412bfe58472bed9fbf500eac
+oid sha256:57d38d2f83edf7948b193d522722e03c4f2b8cbed5067da59897c7f7c3822919
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9e2e9d13f1fab954a76ecc1666482fd90d98438794e386126a6ee156ce5d270
+oid sha256:79354fda314c9103e2d55f6fd0e3e7ec5fe801812e33d2c8e4dd8c180772e09a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb82cfc852da5eb6970b061692451307a303bfd2a3160c6d6a29266f8bb6adef
+oid sha256:6fc750a6dfb3e5c9f642238b7443b0984a56e79b7c2731a6e152ecfc3e32f4e7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.06357356806650773,
+  "epoch": 0.06601870529983496,
   "eval_steps": 34,
-  "global_step": 130,
+  "global_step": 135,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -949,6 +949,41 @@
       "learning_rate": 7.263370099279172e-05,
       "loss": 1.0144,
       "step": 130
+    },
+    {
+      "epoch": 0.06406259551317317,
+      "grad_norm": 0.48772111535072327,
+      "learning_rate": 7.086102531106754e-05,
+      "loss": 1.055,
+      "step": 131
+    },
+    {
+      "epoch": 0.06455162295983861,
+      "grad_norm": 0.37441909313201904,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.948,
+      "step": 132
+    },
+    {
+      "epoch": 0.06504065040650407,
+      "grad_norm": 0.4598063826560974,
+      "learning_rate": 6.734612871599168e-05,
+      "loss": 1.0565,
+      "step": 133
+    },
+    {
+      "epoch": 0.06552967785316952,
+      "grad_norm": 0.34052199125289917,
+      "learning_rate": 6.560510813660719e-05,
+      "loss": 0.9724,
+      "step": 134
+    },
+    {
+      "epoch": 0.06601870529983496,
+      "grad_norm": 0.4426654279232025,
+      "learning_rate": 6.387583338128471e-05,
+      "loss": 1.1751,
+      "step": 135
     }
   ],
   "logging_steps": 1,
@@ -968,7 +1003,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.77064045421527e+17,
+  "total_flos": 5.992588163992781e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null