Training in progress, step 130, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:912c2125854beec112043bed7df3a59b52ffafb2c8e37e37de6b7d6428738e36
+oid sha256:08874706e7b1a7a7cd64c3720795b707e7d35c0b44e86ff47891ff58b63bcb3a
 size 59827904

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0c11c7845b668b903082c2011f56571536b84f2bdfd426b174fcd31b01a682d
+oid sha256:4d985061169075ed36955f62f96c99ddab751a7ce003de76154542284df9b9d1
 size 30875540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:057ecbb0fa4569828a6baa3b23b2b8db44c4a71010246fbd0848ee61061b4c1a
+oid sha256:7525b7a2ec1d973ca3877f2c5945de77129bc1faae8c0b11093d471788249c88
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b577939e8ae09a93269bdd1ffbcc4ef41ec4027476aa914ab19034c5a6ebf492
+oid sha256:fb82cfc852da5eb6970b061692451307a303bfd2a3160c6d6a29266f8bb6adef
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.061128430833180515,
+  "epoch": 0.06357356806650773,
   "eval_steps": 34,
-  "global_step": 125,
+  "global_step": 130,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -914,6 +914,41 @@
       "learning_rate": 8.162504821834295e-05,
       "loss": 8.2794,
       "step": 125
+    },
+    {
+      "epoch": 0.06161745827984596,
+      "grad_norm": 4.274295618404352e+16,
+      "learning_rate": 7.9811759084299e-05,
+      "loss": 8.0011,
+      "step": 126
+    },
+    {
+      "epoch": 0.0621064857265114,
+      "grad_norm": Infinity,
+      "learning_rate": 7.800536421603317e-05,
+      "loss": 8.6106,
+      "step": 127
+    },
+    {
+      "epoch": 0.06259551317317684,
+      "grad_norm": Infinity,
+      "learning_rate": 7.620648049573815e-05,
+      "loss": 8.0169,
+      "step": 128
+    },
+    {
+      "epoch": 0.06308454061984228,
+      "grad_norm": Infinity,
+      "learning_rate": 7.441572224055644e-05,
+      "loss": 9.039,
+      "step": 129
+    },
+    {
+      "epoch": 0.06357356806650773,
+      "grad_norm": Infinity,
+      "learning_rate": 7.263370099279172e-05,
+      "loss": 8.755,
+      "step": 130
     }
   ],
   "logging_steps": 1,
@@ -933,7 +968,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.75559959494656e+17,
+  "total_flos": 2.8658235787444224e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null