Training in progress, step 340, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e58f921024f7d4a3f5be499e38ac1d140150c729cf63f5886172b49d191c20e
+oid sha256:395f189336ee88587c08a855a6366bce7e35606805660d672365db26c72fd926
 size 132164608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5067e99c0251a2e383bd50725f2634c2eb1ccbd90a93ba4cc16d409825011bcc
+oid sha256:fb1e33a31bab7e692ff019d655243137d119d1d215b418632c4a4c1baba39958
 size 67488212

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab4ceaa83c98da3eb4ec0aef1f69381cfa8e51d85f3e4d300d824d547bfebb9f
+oid sha256:55795c4e5c41785c92dfd03c9be6dc5bae6b52fb124698ad8721a4a33a04ef8f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:542eeb761eff9bd2c88163850a5018d7ed947bdab57ea917e6e376b6cb0c0259
+oid sha256:e6999f9aad8d44fbf7db1d80d56ad86630abb8e28a7187e80ed24f8546462146
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1700472353431509,
+  "epoch": 0.18894137260350097,
   "eval_steps": 34,
-  "global_step": 306,
+  "global_step": 340,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -801,6 +801,91 @@
       "eval_samples_per_second": 7.828,
       "eval_steps_per_second": 0.979,
       "step": 306
+    },
+    {
+      "epoch": 0.17171436510141705,
+      "grad_norm": 2.220491886138916,
+      "learning_rate": 6.421379363065142e-06,
+      "loss": 5.3908,
+      "step": 309
+    },
+    {
+      "epoch": 0.17338149485968324,
+      "grad_norm": 2.2047910690307617,
+      "learning_rate": 6.022586521156715e-06,
+      "loss": 5.2721,
+      "step": 312
+    },
+    {
+      "epoch": 0.17504862461794943,
+      "grad_norm": 2.1623401641845703,
+      "learning_rate": 5.634875954308638e-06,
+      "loss": 5.5073,
+      "step": 315
+    },
+    {
+      "epoch": 0.17671575437621562,
+      "grad_norm": 1.9954192638397217,
+      "learning_rate": 5.258474074573877e-06,
+      "loss": 5.1791,
+      "step": 318
+    },
+    {
+      "epoch": 0.1783828841344818,
+      "grad_norm": 2.24808669090271,
+      "learning_rate": 4.893600690050579e-06,
+      "loss": 5.0704,
+      "step": 321
+    },
+    {
+      "epoch": 0.180050013892748,
+      "grad_norm": 2.2592039108276367,
+      "learning_rate": 4.540468876520323e-06,
+      "loss": 5.0177,
+      "step": 324
+    },
+    {
+      "epoch": 0.18171714365101416,
+      "grad_norm": 1.9192252159118652,
+      "learning_rate": 4.199284853017896e-06,
+      "loss": 5.2738,
+      "step": 327
+    },
+    {
+      "epoch": 0.18338427340928035,
+      "grad_norm": 2.021440267562866,
+      "learning_rate": 3.8702478614051355e-06,
+      "loss": 4.6439,
+      "step": 330
+    },
+    {
+      "epoch": 0.18505140316754654,
+      "grad_norm": 2.309406042098999,
+      "learning_rate": 3.5535500500193357e-06,
+      "loss": 5.4409,
+      "step": 333
+    },
+    {
+      "epoch": 0.18671853292581272,
+      "grad_norm": 2.2390878200531006,
+      "learning_rate": 3.249376361464021e-06,
+      "loss": 5.1074,
+      "step": 336
+    },
+    {
+      "epoch": 0.18838566268407891,
+      "grad_norm": 2.540015697479248,
+      "learning_rate": 2.957904424607652e-06,
+      "loss": 5.2675,
+      "step": 339
+    },
+    {
+      "epoch": 0.18894137260350097,
+      "eval_loss": 1.2895426750183105,
+      "eval_runtime": 387.2989,
+      "eval_samples_per_second": 7.826,
+      "eval_steps_per_second": 0.979,
+      "step": 340
     }
   ],
   "logging_steps": 3,
@@ -820,7 +905,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.10135319642112e+17,
+  "total_flos": 6.76579980398592e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null