Training in progress, step 306, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c7e6d9652442fa642063424b204e43fa7e18c77cf6990911220075103af0998
+oid sha256:071f7490848f8db3ad947d28a481e886b6fde2c39706ecda5845c4bc262c6edc
 size 72396376

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b739aced26e02b72f0f4376d4b8e542febe656c5c4972b6b6ed9a4685b22ac00
+oid sha256:a5406715c6c25e67ddc39831f5deb857fe1d7b8610da87d62b53c698479ed0c0
 size 37134740

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecc873a6b8b4dda97e1cfd6b2b58261bd5e2dd33f35d84c167b41efe0afbcd31
+oid sha256:686cb4067140cd81e5c35c9c423deb1a7cd2b969cc1b59549029227a11d67047
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3520b6e9bfde48b403dd6f4096e526132e910f4d92bd802fb2e831d46f8ad41f
+oid sha256:542eeb761eff9bd2c88163850a5018d7ed947bdab57ea917e6e376b6cb0c0259
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.07733864088711971,
+  "epoch": 0.08700597099800966,
   "eval_steps": 34,
-  "global_step": 272,
+  "global_step": 306,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -709,6 +709,98 @@
       "eval_samples_per_second": 35.254,
       "eval_steps_per_second": 4.41,
       "step": 272
+    },
+    {
+      "epoch": 0.07762297412567529,
+      "grad_norm": 0.6064507961273193,
+      "learning_rate": 1.1980489393370938e-05,
+      "loss": 0.4708,
+      "step": 273
+    },
+    {
+      "epoch": 0.07847597384134206,
+      "grad_norm": 0.7535691261291504,
+      "learning_rate": 1.1468581814301717e-05,
+      "loss": 0.426,
+      "step": 276
+    },
+    {
+      "epoch": 0.07932897355700881,
+      "grad_norm": 0.5106021165847778,
+      "learning_rate": 1.096457620240298e-05,
+      "loss": 0.457,
+      "step": 279
+    },
+    {
+      "epoch": 0.08018197327267558,
+      "grad_norm": 0.7610855102539062,
+      "learning_rate": 1.0468766882759094e-05,
+      "loss": 0.3867,
+      "step": 282
+    },
+    {
+      "epoch": 0.08103497298834234,
+      "grad_norm": 0.57286137342453,
+      "learning_rate": 9.981443394050525e-06,
+      "loss": 0.4744,
+      "step": 285
+    },
+    {
+      "epoch": 0.0818879727040091,
+      "grad_norm": 0.6350270509719849,
+      "learning_rate": 9.502890319471491e-06,
+      "loss": 0.4382,
+      "step": 288
+    },
+    {
+      "epoch": 0.08274097241967586,
+      "grad_norm": 0.5878217816352844,
+      "learning_rate": 9.033387120541306e-06,
+      "loss": 0.4471,
+      "step": 291
+    },
+    {
+      "epoch": 0.08359397213534261,
+      "grad_norm": 0.4584065079689026,
+      "learning_rate": 8.573207973906735e-06,
+      "loss": 0.4223,
+      "step": 294
+    },
+    {
+      "epoch": 0.08444697185100938,
+      "grad_norm": 0.514761745929718,
+      "learning_rate": 8.1226216112306e-06,
+      "loss": 0.4439,
+      "step": 297
+    },
+    {
+      "epoch": 0.08529997156667614,
+      "grad_norm": 0.4604704678058624,
+      "learning_rate": 7.681891162260015e-06,
+      "loss": 0.4769,
+      "step": 300
+    },
+    {
+      "epoch": 0.08615297128234291,
+      "grad_norm": 0.5754848718643188,
+      "learning_rate": 7.251274001166044e-06,
+      "loss": 0.4719,
+      "step": 303
+    },
+    {
+      "epoch": 0.08700597099800966,
+      "grad_norm": 0.6474661827087402,
+      "learning_rate": 6.831021596244424e-06,
+      "loss": 0.3843,
+      "step": 306
+    },
+    {
+      "epoch": 0.08700597099800966,
+      "eval_loss": 0.4252224862575531,
+      "eval_runtime": 168.0333,
+      "eval_samples_per_second": 35.255,
+      "eval_steps_per_second": 4.41,
+      "step": 306
     }
   ],
   "logging_steps": 3,
@@ -728,7 +820,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.710400478963302e+16,
+  "total_flos": 9.799200538833715e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null