Training in progress, step 78, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b004125126c5ffcd7f5a52278582e0bbca469d3c94482cf7c834c9174f9bb268
+oid sha256:0696594f83839f848a9fb64316cd8f0fa1678b6a6ebd76756d0417be0a738d2d
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58626b946af51b020c1453719a4944beb19c24f35d12db6a55983a848644b8a4
+oid sha256:f433fdbdda0f9a302c42618afafd1488d146199d9b0e84b79c28cab70c4b869a
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d52029764bce6b207ece38b8ac6ef3a9c9a1677d93ff032b9d0c8abcf44917a
+oid sha256:d0bfe203dcc9b3b030e44f5295d53d381de790a5365f0913e245991089bf10fb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb438ab9499d5178d553290d304fad6bd105cd4f59f8f03d9657a249b7bd5f14
+oid sha256:a4d6e5f76805b36e4d76ee2a3b48ba3bedb1c2bda79be4f5c70f809dd0d57438
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01800055386319579,
+  "epoch": 0.02160066463583495,
   "eval_steps": 13,
-  "global_step": 65,
+  "global_step": 78,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -202,6 +202,49 @@
       "eval_samples_per_second": 13.193,
       "eval_steps_per_second": 1.651,
       "step": 65
+    },
+    {
+      "epoch": 0.01827748546109111,
+      "grad_norm": 26.79857063293457,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.5632,
+      "step": 66
+    },
+    {
+      "epoch": 0.01910828025477707,
+      "grad_norm": 1.9956955909729004,
+      "learning_rate": 6.22170203068947e-05,
+      "loss": 1.4358,
+      "step": 69
+    },
+    {
+      "epoch": 0.01993907504846303,
+      "grad_norm": 4.290536403656006,
+      "learning_rate": 5.8927844739931834e-05,
+      "loss": 1.3875,
+      "step": 72
+    },
+    {
+      "epoch": 0.02076986984214899,
+      "grad_norm": 2.6607825756073,
+      "learning_rate": 5.559822380516539e-05,
+      "loss": 1.5102,
+      "step": 75
+    },
+    {
+      "epoch": 0.02160066463583495,
+      "grad_norm": 3.075331687927246,
+      "learning_rate": 5.2243241517525754e-05,
+      "loss": 1.3868,
+      "step": 78
+    },
+    {
+      "epoch": 0.02160066463583495,
+      "eval_loss": 0.3655809164047241,
+      "eval_runtime": 461.183,
+      "eval_samples_per_second": 13.188,
+      "eval_steps_per_second": 1.65,
+      "step": 78
     }
   ],
   "logging_steps": 3,
@@ -221,7 +264,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0477654222307328e+17,
+  "total_flos": 1.2672972249838387e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null