Training in progress, step 135, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08874706e7b1a7a7cd64c3720795b707e7d35c0b44e86ff47891ff58b63bcb3a
+oid sha256:99cfac1c2baddf1f9ea0d4faa7680daa5c2e80d219f5986eddd54fd836006122
 size 59827904

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d985061169075ed36955f62f96c99ddab751a7ce003de76154542284df9b9d1
+oid sha256:1a18d2c0a01d50a4c51715dadf4a0be0be51dc97452581044464ba783c996e19
 size 30875540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7525b7a2ec1d973ca3877f2c5945de77129bc1faae8c0b11093d471788249c88
+oid sha256:392da1c3f18aef86ac42978c5ab2b3ef58330aa9d54adc511669e79f01b39081
 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": 8.755,
       "step": 130
+    },
+    {
+      "epoch": 0.06406259551317317,
+      "grad_norm": Infinity,
+      "learning_rate": 7.086102531106754e-05,
+      "loss": 10.3864,
+      "step": 131
+    },
+    {
+      "epoch": 0.06455162295983861,
+      "grad_norm": Infinity,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 8.9227,
+      "step": 132
+    },
+    {
+      "epoch": 0.06504065040650407,
+      "grad_norm": Infinity,
+      "learning_rate": 6.734612871599168e-05,
+      "loss": 7.8021,
+      "step": 133
+    },
+    {
+      "epoch": 0.06552967785316952,
+      "grad_norm": Infinity,
+      "learning_rate": 6.560510813660719e-05,
+      "loss": 9.1572,
+      "step": 134
+    },
+    {
+      "epoch": 0.06601870529983496,
+      "grad_norm": Infinity,
+      "learning_rate": 6.387583338128471e-05,
+      "loss": 9.7205,
+      "step": 135
     }
   ],
   "logging_steps": 1,
@@ -968,7 +1003,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.8658235787444224e+17,
+  "total_flos": 2.976047562542285e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null