Training in progress, step 294, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18d3d88ed93966722511e1fd83bc9e5a29664dc928eaf28d3ef2ef1c16720d1f
+oid sha256:8dfd39d0e918f52073c6d797146c5a4cc8d71bef64bfd25f35e08d84c0cae024
 size 313820248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cb26a28b4f259288dad56068545379587b60becf2baf1dcdeef689747c983ad
-size 159641092
+oid sha256:b2ea606a77a785082c6c5e1b7cd44520ed885f2227842265f6cd0c1ebe19417e
+size 159641284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24c351254b01cc68c87af0db48cd5f3e1b6768bd4a213369e7028441ce047b0d
+oid sha256:e97da99bcea15f94303530a0ce03b8a68986e36bb82581fb2057e7273237f605
 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": 0.42857142857142855,
+  "epoch": 0.5,
   "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": 28.13,
       "eval_steps_per_second": 3.523,
       "step": 252
+    },
+    {
+      "epoch": 0.4336734693877551,
+      "grad_norm": 1.393947958946228,
+      "learning_rate": 5e-05,
+      "loss": 1.4025,
+      "step": 255
+    },
+    {
+      "epoch": 0.4387755102040816,
+      "grad_norm": 1.2842843532562256,
+      "learning_rate": 4.903834726061565e-05,
+      "loss": 1.3806,
+      "step": 258
+    },
+    {
+      "epoch": 0.44387755102040816,
+      "grad_norm": 1.4686455726623535,
+      "learning_rate": 4.807705027948008e-05,
+      "loss": 1.3954,
+      "step": 261
+    },
+    {
+      "epoch": 0.4489795918367347,
+      "grad_norm": 1.3992563486099243,
+      "learning_rate": 4.711646468323129e-05,
+      "loss": 1.3417,
+      "step": 264
+    },
+    {
+      "epoch": 0.45408163265306123,
+      "grad_norm": 1.3817628622055054,
+      "learning_rate": 4.6156945835334184e-05,
+      "loss": 1.4016,
+      "step": 267
+    },
+    {
+      "epoch": 0.45918367346938777,
+      "grad_norm": 1.4665182828903198,
+      "learning_rate": 4.5198848704615914e-05,
+      "loss": 1.3706,
+      "step": 270
+    },
+    {
+      "epoch": 0.4642857142857143,
+      "grad_norm": 1.3997013568878174,
+      "learning_rate": 4.424252773394704e-05,
+      "loss": 1.4081,
+      "step": 273
+    },
+    {
+      "epoch": 0.46938775510204084,
+      "grad_norm": 1.4313600063323975,
+      "learning_rate": 4.328833670911724e-05,
+      "loss": 1.4345,
+      "step": 276
+    },
+    {
+      "epoch": 0.4744897959183674,
+      "grad_norm": 1.2777554988861084,
+      "learning_rate": 4.23366286279542e-05,
+      "loss": 1.3368,
+      "step": 279
+    },
+    {
+      "epoch": 0.47959183673469385,
+      "grad_norm": 1.297582745552063,
+      "learning_rate": 4.138775556973406e-05,
+      "loss": 1.411,
+      "step": 282
+    },
+    {
+      "epoch": 0.4846938775510204,
+      "grad_norm": 1.409166693687439,
+      "learning_rate": 4.04420685649314e-05,
+      "loss": 1.4427,
+      "step": 285
+    },
+    {
+      "epoch": 0.4897959183673469,
+      "grad_norm": 1.392500400543213,
+      "learning_rate": 3.9499917465357534e-05,
+      "loss": 1.4439,
+      "step": 288
+    },
+    {
+      "epoch": 0.49489795918367346,
+      "grad_norm": 1.3200541734695435,
+      "learning_rate": 3.856165081473474e-05,
+      "loss": 1.39,
+      "step": 291
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.4324284791946411,
+      "learning_rate": 3.762761571975429e-05,
+      "loss": 1.3971,
+      "step": 294
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 1.3641271591186523,
+      "eval_runtime": 35.1729,
+      "eval_samples_per_second": 28.147,
+      "eval_steps_per_second": 3.525,
+      "step": 294
     }
   ],
   "logging_steps": 3,
@@ -670,7 +776,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0207954482285773e+17,
+  "total_flos": 1.1909280229333402e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null