Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43cc6e7e411cda4b8ae94679405c4a4281e94c5985662ea8fd836b73886336ff
+oid sha256:b7da853ddb95921974e632bf94c345733e908f363824660d29ad784a831828e6
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:743fbaf6be0c7b24554a843847d8803e1ec03ce026002941f7b9926372974e82
+oid sha256:cb1e841d25796de3bbcd9e9decf1f12ba1be4af619a401bf863bcc5f36a733dc
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:039829e04be7e3c1216201121a1138b47be62b9a78e566a43e535362c7a36b51
+oid sha256:62d22e03c59e72d7ff5f55cc60f3b0f88639286073a59c071c323c5733d4d9e2
 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": 0.008175946365791841,
+  "epoch": 0.016351892731583682,
   "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": 57.685,
       "eval_steps_per_second": 28.854,
       "step": 50
+    },
+    {
+      "epoch": 0.009811135638950209,
+      "grad_norm": 1.3060485124588013,
+      "learning_rate": 0.00016324453755953773,
+      "loss": 1.5988,
+      "step": 60
+    },
+    {
+      "epoch": 0.011446324912108577,
+      "grad_norm": 1.2081083059310913,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.6312,
+      "step": 70
+    },
+    {
+      "epoch": 0.013081514185266945,
+      "grad_norm": 1.0915815830230713,
+      "learning_rate": 0.00013546048870425356,
+      "loss": 1.6993,
+      "step": 80
+    },
+    {
+      "epoch": 0.014716703458425313,
+      "grad_norm": 1.5986297130584717,
+      "learning_rate": 0.00012000256937760445,
+      "loss": 1.6293,
+      "step": 90
+    },
+    {
+      "epoch": 0.016351892731583682,
+      "grad_norm": 1.1840400695800781,
+      "learning_rate": 0.00010402659401094152,
+      "loss": 1.5559,
+      "step": 100
+    },
+    {
+      "epoch": 0.016351892731583682,
+      "eval_loss": 1.7379602193832397,
+      "eval_runtime": 44.7506,
+      "eval_samples_per_second": 57.541,
+      "eval_steps_per_second": 28.782,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 445190819020800.0,
+  "total_flos": 890381638041600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null