Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc6fe706f53dcdc54b1856c209ea279c34d9fd1815f7fb6c93e5cc72b3857052
+oid sha256:0e717051db4ab97e73f2485a7367bebab4e7b7de93e2f9cf15bd1b4bba566a62
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a9431b87fc3033f30e0748bbe7c8786d845e952f86233764e824484a8013da8
+oid sha256:4edefea009e9a09eb254880cb994ab68d2b5dc333f3681a7c3b92c563e39e59a
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f5bb684d43b55b5c356875e0d684b638055f91504d83fe8b7e6cef8067899b5
+oid sha256:31e34151931fc20b73b6d39ac7bf6d8a26c411189b10b0b99732ef2e9f23ba3d
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a87a83fbdff267a8a8ccc8be8ea014bdd0146d547acdfc7cd966c4e785a37d18
+oid sha256:a0024c4472ba90a9b0d2a07e0f3351725e659de04eb3d575ab784e945d373480
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:118a56b8415fb7ef98699cbabd3bc88b6415e112084644328b851c58e61558ac
+oid sha256:66375789b58d5126937de8e5294e0b1c96251b7abde314308b8d04385f7f6368
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be4959782f5bf0affaa4928a858f01d42a74a493524e6eb9bd6583a34ce6c4cc
+oid sha256:e4b7b15ba444c816a58b461a4ac9a469d230c4bc50648f9c62cab13767b03d22
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.036218761318362915,
+  "epoch": 0.07243752263672583,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 43.069,
       "eval_steps_per_second": 11.198,
       "step": 25
+    },
+    {
+      "epoch": 0.03766751177109743,
+      "grad_norm": 1.519792914390564,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.6345,
+      "step": 26
+    },
+    {
+      "epoch": 0.039116262223831945,
+      "grad_norm": 0.8911117315292358,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.5823,
+      "step": 27
+    },
+    {
+      "epoch": 0.04056501267656646,
+      "grad_norm": 0.8245032429695129,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.5606,
+      "step": 28
+    },
+    {
+      "epoch": 0.042013763129300975,
+      "grad_norm": 0.8425853848457336,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.5497,
+      "step": 29
+    },
+    {
+      "epoch": 0.0434625135820355,
+      "grad_norm": 1.2193143367767334,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.5908,
+      "step": 30
+    },
+    {
+      "epoch": 0.04491126403477001,
+      "grad_norm": 1.1511098146438599,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.5944,
+      "step": 31
+    },
+    {
+      "epoch": 0.04636001448750453,
+      "grad_norm": 0.8153553605079651,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.5599,
+      "step": 32
+    },
+    {
+      "epoch": 0.04780876494023904,
+      "grad_norm": 0.9374620914459229,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.5604,
+      "step": 33
+    },
+    {
+      "epoch": 0.04925751539297356,
+      "grad_norm": 0.5474502444267273,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.5657,
+      "step": 34
+    },
+    {
+      "epoch": 0.05070626584570807,
+      "grad_norm": 0.7612038254737854,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.5785,
+      "step": 35
+    },
+    {
+      "epoch": 0.052155016298442596,
+      "grad_norm": 0.6650935411453247,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.5666,
+      "step": 36
+    },
+    {
+      "epoch": 0.05360376675117711,
+      "grad_norm": 0.7727776169776917,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.5634,
+      "step": 37
+    },
+    {
+      "epoch": 0.055052517203911626,
+      "grad_norm": 0.5608248114585876,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.5904,
+      "step": 38
+    },
+    {
+      "epoch": 0.05650126765664614,
+      "grad_norm": 0.879086434841156,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.5817,
+      "step": 39
+    },
+    {
+      "epoch": 0.057950018109380656,
+      "grad_norm": 0.8060774207115173,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.5599,
+      "step": 40
+    },
+    {
+      "epoch": 0.05939876856211518,
+      "grad_norm": 0.7871993184089661,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.5396,
+      "step": 41
+    },
+    {
+      "epoch": 0.060847519014849694,
+      "grad_norm": 0.3978239893913269,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.5451,
+      "step": 42
+    },
+    {
+      "epoch": 0.06229626946758421,
+      "grad_norm": 0.7827884554862976,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.5745,
+      "step": 43
+    },
+    {
+      "epoch": 0.06374501992031872,
+      "grad_norm": 1.1979758739471436,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.5875,
+      "step": 44
+    },
+    {
+      "epoch": 0.06519377037305324,
+      "grad_norm": 1.3340702056884766,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.5744,
+      "step": 45
+    },
+    {
+      "epoch": 0.06664252082578775,
+      "grad_norm": 1.1701022386550903,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.5734,
+      "step": 46
+    },
+    {
+      "epoch": 0.06809127127852227,
+      "grad_norm": 1.051703691482544,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.5751,
+      "step": 47
+    },
+    {
+      "epoch": 0.06954002173125678,
+      "grad_norm": 0.8547968864440918,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.5754,
+      "step": 48
+    },
+    {
+      "epoch": 0.07098877218399131,
+      "grad_norm": 0.6540709137916565,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.5709,
+      "step": 49
+    },
+    {
+      "epoch": 0.07243752263672583,
+      "grad_norm": 0.7267070412635803,
+      "learning_rate": 1e-05,
+      "loss": 1.5731,
+      "step": 50
+    },
+    {
+      "epoch": 0.07243752263672583,
+      "eval_loss": 1.5619583129882812,
+      "eval_runtime": 1.1496,
+      "eval_samples_per_second": 43.492,
+      "eval_steps_per_second": 11.308,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -212,12 +395,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5.304303857382195e+16,
+  "total_flos": 1.0606952192776602e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null