Training in progress, step 130, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1080c2dcf21c0b41e7ea16ba47e965a1a0bc3cba9fab02708c6b5bd830c931b2
+oid sha256:81c631790391462074f7254948e2937b8d20f618f4411a2eb2bd8919e480a821
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e8cc1a90bf0d92d37ea0e0431dd8f7cb23cc35f1625edfceb841ebbccf62d51
+oid sha256:ecbe9f1bd7b567eef8ff0b47d85ebde84bef5328a324b5eb82318b5f61dffdd4
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86748f5994a634f58ece1ba5cddd089ee5a870e039bbcbeb2cee4742ee257abe
+oid sha256:3ebcfbe921966314e6f2c12a21ae76e083d0bfa3c62fc82a12af734431287d92
 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": 1.2018,
       "step": 125
+    },
+    {
+      "epoch": 0.06161745827984596,
+      "grad_norm": 1.4820826053619385,
+      "learning_rate": 7.9811759084299e-05,
+      "loss": 1.102,
+      "step": 126
+    },
+    {
+      "epoch": 0.0621064857265114,
+      "grad_norm": 1.699189305305481,
+      "learning_rate": 7.800536421603317e-05,
+      "loss": 1.161,
+      "step": 127
+    },
+    {
+      "epoch": 0.06259551317317684,
+      "grad_norm": 1.9508938789367676,
+      "learning_rate": 7.620648049573815e-05,
+      "loss": 1.1853,
+      "step": 128
+    },
+    {
+      "epoch": 0.06308454061984228,
+      "grad_norm": 1.7746766805648804,
+      "learning_rate": 7.441572224055644e-05,
+      "loss": 1.1611,
+      "step": 129
+    },
+    {
+      "epoch": 0.06357356806650773,
+      "grad_norm": 1.4383032321929932,
+      "learning_rate": 7.263370099279172e-05,
+      "loss": 1.0862,
+      "step": 130
     }
   ],
   "logging_steps": 1,
@@ -933,7 +968,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.2163654631424e+16,
+  "total_flos": 7.505020081668096e+16,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null