Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e02d256176dec56910369921ddf8305dda8a5255cff9a01bfff3f432d891012
+oid sha256:fbba7a0bf2edc23f83f8b981b62aa709bd95562abc38692dee31d2b8b96fc6c3
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be71ad7c84ba6026afecfb992a7227474bd9a9526bef2e0e549882060f53b361
+oid sha256:1d4c643012562ca3c451d24ee8d0ab81d050e42ccf5d9b85a19de57196c9affa
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cb7035846890a6ac76465b32c5f991b58c5c60e16b215999fae555f18de2774
+oid sha256:e38b43bb216852b411c1d270f1be8fb468fb40b1ffedbc6087e027f8c704135f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8148b27980adb9b0bdd5c04049e531bfefcc05c06612ee72169cfb9b9fd7ee7
+oid sha256:0fd8212ec5ec3406d74a7f927b717dd30ea8a06115ee6582e14976f7b84b4b58
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.07366482504604052,
+  "epoch": 0.14732965009208104,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 30.146,
       "eval_steps_per_second": 15.073,
       "step": 50
+    },
+    {
+      "epoch": 0.08839779005524862,
+      "grad_norm": 9.087752342224121,
+      "learning_rate": 0.00016324453755953773,
+      "loss": 9.2702,
+      "step": 60
+    },
+    {
+      "epoch": 0.10313075506445672,
+      "grad_norm": 7.378783702850342,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 8.6637,
+      "step": 70
+    },
+    {
+      "epoch": 0.11786372007366483,
+      "grad_norm": 8.353407859802246,
+      "learning_rate": 0.00013546048870425356,
+      "loss": 8.1776,
+      "step": 80
+    },
+    {
+      "epoch": 0.13259668508287292,
+      "grad_norm": 5.851109504699707,
+      "learning_rate": 0.00012000256937760445,
+      "loss": 6.9892,
+      "step": 90
+    },
+    {
+      "epoch": 0.14732965009208104,
+      "grad_norm": 6.5868635177612305,
+      "learning_rate": 0.00010402659401094152,
+      "loss": 7.9818,
+      "step": 100
+    },
+    {
+      "epoch": 0.14732965009208104,
+      "eval_loss": 1.9617358446121216,
+      "eval_runtime": 9.4797,
+      "eval_samples_per_second": 30.17,
+      "eval_steps_per_second": 15.085,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8184464941252608.0,
+  "total_flos": 1.6368929882505216e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null