Training in progress, step 294, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53a348c6d3b4191796ffdabcb14604ee130d298901567610f85281a7536083d7
+oid sha256:7cc948873caa08921327726f20f406c613f84022f629a8b1be0e9b9d5c8d1f31
 size 93608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:987a783489dce67d0b3d68f3de305221db1ac97b9e30bbe55c7bb295fe17364f
+oid sha256:77ad83b8581d98d467b489581929046033ba13e2931665a83fafd2a14bfad6bf
 size 197158

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29911251ace24c40b79674cb166908f96c7002d4886d0edd0086760eef5b7703
+oid sha256:37abdf82049403a03d10ecacdbbeb17537569cc71638264b2a476090c2ddcbf8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee19ddad9c4c375a1de2d74fb4c1cf5e15d36c1ed47a2cb80f7cb0fbacb3b29e
+oid sha256:318b114b83c26bcba11815378a88e0015bce044b0002c702e0a2627e1a1d1e56
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7128712871287128,
+  "epoch": 0.8316831683168316,
   "eval_steps": 42,
-  "global_step": 252,
+  "global_step": 294,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -651,6 +651,112 @@
       "eval_samples_per_second": 93.539,
       "eval_steps_per_second": 11.771,
       "step": 252
+    },
+    {
+      "epoch": 0.7213578500707214,
+      "grad_norm": 0.050791915506124496,
+      "learning_rate": 5e-05,
+      "loss": 11.8143,
+      "step": 255
+    },
+    {
+      "epoch": 0.7298444130127298,
+      "grad_norm": 0.1059621125459671,
+      "learning_rate": 4.903834726061565e-05,
+      "loss": 11.8175,
+      "step": 258
+    },
+    {
+      "epoch": 0.7383309759547383,
+      "grad_norm": 0.07910209894180298,
+      "learning_rate": 4.807705027948008e-05,
+      "loss": 11.8104,
+      "step": 261
+    },
+    {
+      "epoch": 0.7468175388967468,
+      "grad_norm": 0.11326657980680466,
+      "learning_rate": 4.711646468323129e-05,
+      "loss": 11.8178,
+      "step": 264
+    },
+    {
+      "epoch": 0.7553041018387553,
+      "grad_norm": 0.15818099677562714,
+      "learning_rate": 4.6156945835334184e-05,
+      "loss": 11.8152,
+      "step": 267
+    },
+    {
+      "epoch": 0.7637906647807637,
+      "grad_norm": 0.08803381770849228,
+      "learning_rate": 4.5198848704615914e-05,
+      "loss": 11.8165,
+      "step": 270
+    },
+    {
+      "epoch": 0.7722772277227723,
+      "grad_norm": 0.13214413821697235,
+      "learning_rate": 4.424252773394704e-05,
+      "loss": 11.8183,
+      "step": 273
+    },
+    {
+      "epoch": 0.7807637906647807,
+      "grad_norm": 0.0714588537812233,
+      "learning_rate": 4.328833670911724e-05,
+      "loss": 11.8207,
+      "step": 276
+    },
+    {
+      "epoch": 0.7892503536067893,
+      "grad_norm": 0.3612169325351715,
+      "learning_rate": 4.23366286279542e-05,
+      "loss": 11.81,
+      "step": 279
+    },
+    {
+      "epoch": 0.7977369165487977,
+      "grad_norm": 0.10489798337221146,
+      "learning_rate": 4.138775556973406e-05,
+      "loss": 11.8155,
+      "step": 282
+    },
+    {
+      "epoch": 0.8062234794908062,
+      "grad_norm": 0.07869977504014969,
+      "learning_rate": 4.04420685649314e-05,
+      "loss": 11.8183,
+      "step": 285
+    },
+    {
+      "epoch": 0.8147100424328148,
+      "grad_norm": 0.1785990297794342,
+      "learning_rate": 3.9499917465357534e-05,
+      "loss": 11.8151,
+      "step": 288
+    },
+    {
+      "epoch": 0.8231966053748232,
+      "grad_norm": 0.08096058666706085,
+      "learning_rate": 3.856165081473474e-05,
+      "loss": 11.8138,
+      "step": 291
+    },
+    {
+      "epoch": 0.8316831683168316,
+      "grad_norm": 0.11269628256559372,
+      "learning_rate": 3.762761571975429e-05,
+      "loss": 11.8173,
+      "step": 294
+    },
+    {
+      "epoch": 0.8316831683168316,
+      "eval_loss": 11.817937850952148,
+      "eval_runtime": 6.604,
+      "eval_samples_per_second": 90.248,
+      "eval_steps_per_second": 11.357,
+      "step": 294
     }
   ],
   "logging_steps": 3,
@@ -670,7 +776,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1549896253440.0,
+  "total_flos": 1802989731840.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null