Training in progress, step 95, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cc30f1e357080bd583aaba94cad79247586b36f29d35647d75bd19ccc7e18b8
+oid sha256:75cbc872c534a49966396c255341d9ff2c917040c39e7f926f7533577d857cc2
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64885af957151ce4958b0e044f7ed2e3e471dca64d4388e096a94408b85ba248
+oid sha256:0679492656c17132b1f8d6498337064990d913e068a9db428d6dc866229a749a
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdf18d6697609a27a0b488fa23bfd024570519524cd30dfeaa261a878e17c189
+oid sha256:710b3f208bedd5f0fd57c1f63cb3947d4bf432afdfc4b07fd7ad25fb3ae74fb4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfdc0543e9ce40f0d0b0ee9752d10d130598c759cc5a2bd973736f6096894d17
+oid sha256:3160dd3097641f3bf4d4036c0ddfd8673184925120f088b5ebecc6a1e5c953dd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04401247019988997,
+  "epoch": 0.04645760743321719,
   "eval_steps": 34,
-  "global_step": 90,
+  "global_step": 95,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -661,6 +661,41 @@
       "learning_rate": 0.00014457383557765386,
       "loss": 0.993,
       "step": 90
+    },
+    {
+      "epoch": 0.044501497646555414,
+      "grad_norm": 0.39897996187210083,
+      "learning_rate": 0.0001429120608772609,
+      "loss": 1.0264,
+      "step": 91
+    },
+    {
+      "epoch": 0.04499052509322086,
+      "grad_norm": 0.2525433897972107,
+      "learning_rate": 0.00014123563174739037,
+      "loss": 1.0285,
+      "step": 92
+    },
+    {
+      "epoch": 0.0454795525398863,
+      "grad_norm": 0.2693867087364197,
+      "learning_rate": 0.00013954512068705424,
+      "loss": 0.9909,
+      "step": 93
+    },
+    {
+      "epoch": 0.045968579986551746,
+      "grad_norm": 0.4188447594642639,
+      "learning_rate": 0.00013784110500423104,
+      "loss": 0.9365,
+      "step": 94
+    },
+    {
+      "epoch": 0.04645760743321719,
+      "grad_norm": 0.3923894762992859,
+      "learning_rate": 0.00013612416661871533,
+      "loss": 1.187,
+      "step": 95
     }
   ],
   "logging_steps": 1,
@@ -680,7 +715,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.995058775995187e+17,
+  "total_flos": 4.2170064857726976e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null