Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54517286270f685372acb949ac572474c53c8179031351b0278a603921a28579
+oid sha256:0732a89aad87e4b5832b5ac0791b75105e96eb4e070ba1c83447440a0c8c5678
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:943f6b4cc56f0ccd65bd5579b7eecc460cdf1bfc7876ef7ed8e14a101b6e7b97
+oid sha256:6d11a46bc9025dc9cc3ece58f49a0076abc1dc66179acff45130958219df200e
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84a495b0b49dc7e5209961d24d95cf5b1b284099292b40a5de763d213f823202
+oid sha256:3da9138eed4e5bfe7d01017e32088b3727d0b4a06e9efed0e89cb0b6d2c7d72c
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f73ff5518c4f42cd4b9f421ef9a24df1dbbc7496cfc5d9d4259f70f74da53d91
+oid sha256:fe59ffd381afffc0c19e45c9f632b42fa8ecc2c4f39c890c9416396034d3f3ca
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff97097e47371e7cc2cb969474e61c57a532f8a8bcb6df3dfd18b471085967ed
+oid sha256:e54a472b37f6bba44fda0bebab7623b7c17b18d0cce3ab17ce5eb16eb5fccfaf
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:234c315011a9b2d9218840fb5554f6cde05d3ded9a306c6f00a9bb1db7cbb431
+oid sha256:fb0a88b2e9325856ce03b711f6a3250f99f4a9248e4f565df8db4afb5c5e64bb
 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": 0.03707136237256719,
+  "epoch": 0.07414272474513438,
   "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": 14.372,
       "eval_steps_per_second": 3.737,
       "step": 25
+    },
+    {
+      "epoch": 0.03855421686746988,
+      "grad_norm": 15.813837051391602,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 5.8473,
+      "step": 26
+    },
+    {
+      "epoch": 0.04003707136237257,
+      "grad_norm": 13.459531784057617,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 5.7006,
+      "step": 27
+    },
+    {
+      "epoch": 0.04151992585727526,
+      "grad_norm": 7.003750324249268,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 5.5551,
+      "step": 28
+    },
+    {
+      "epoch": 0.043002780352177944,
+      "grad_norm": 2.730677843093872,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 5.4208,
+      "step": 29
+    },
+    {
+      "epoch": 0.04448563484708063,
+      "grad_norm": 1.527279019355774,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 5.3499,
+      "step": 30
+    },
+    {
+      "epoch": 0.04596848934198332,
+      "grad_norm": 1.468549132347107,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 5.3628,
+      "step": 31
+    },
+    {
+      "epoch": 0.047451343836886005,
+      "grad_norm": 1.2678706645965576,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 5.3599,
+      "step": 32
+    },
+    {
+      "epoch": 0.04893419833178869,
+      "grad_norm": 1.247628092765808,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 5.3066,
+      "step": 33
+    },
+    {
+      "epoch": 0.05041705282669138,
+      "grad_norm": 1.016780972480774,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 5.3093,
+      "step": 34
+    },
+    {
+      "epoch": 0.051899907321594066,
+      "grad_norm": 1.0291693210601807,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 5.32,
+      "step": 35
+    },
+    {
+      "epoch": 0.05338276181649675,
+      "grad_norm": 1.1711857318878174,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 5.3058,
+      "step": 36
+    },
+    {
+      "epoch": 0.05486561631139945,
+      "grad_norm": 1.3060027360916138,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 5.3427,
+      "step": 37
+    },
+    {
+      "epoch": 0.056348470806302134,
+      "grad_norm": 1.1797828674316406,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 5.2493,
+      "step": 38
+    },
+    {
+      "epoch": 0.05783132530120482,
+      "grad_norm": 1.2685225009918213,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 5.2396,
+      "step": 39
+    },
+    {
+      "epoch": 0.05931417979610751,
+      "grad_norm": 1.1514685153961182,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 5.1973,
+      "step": 40
+    },
+    {
+      "epoch": 0.060797034291010195,
+      "grad_norm": 0.915943443775177,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 5.2604,
+      "step": 41
+    },
+    {
+      "epoch": 0.06227988878591288,
+      "grad_norm": 0.7309096455574036,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 5.2574,
+      "step": 42
+    },
+    {
+      "epoch": 0.06376274328081558,
+      "grad_norm": 0.6121890544891357,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 5.237,
+      "step": 43
+    },
+    {
+      "epoch": 0.06524559777571826,
+      "grad_norm": 0.5316140651702881,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 5.2674,
+      "step": 44
+    },
+    {
+      "epoch": 0.06672845227062095,
+      "grad_norm": 0.5401632189750671,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 5.2222,
+      "step": 45
+    },
+    {
+      "epoch": 0.06821130676552363,
+      "grad_norm": 1.0013433694839478,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 5.1911,
+      "step": 46
+    },
+    {
+      "epoch": 0.06969416126042632,
+      "grad_norm": 0.9075887203216553,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 5.2855,
+      "step": 47
+    },
+    {
+      "epoch": 0.071177015755329,
+      "grad_norm": 1.1342015266418457,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 5.2796,
+      "step": 48
+    },
+    {
+      "epoch": 0.0726598702502317,
+      "grad_norm": 1.9507712125778198,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 5.2357,
+      "step": 49
+    },
+    {
+      "epoch": 0.07414272474513438,
+      "grad_norm": 2.180121898651123,
+      "learning_rate": 1e-05,
+      "loss": 5.3245,
+      "step": 50
+    },
+    {
+      "epoch": 0.07414272474513438,
+      "eval_loss": 5.244147777557373,
+      "eval_runtime": 3.4601,
+      "eval_samples_per_second": 14.45,
+      "eval_steps_per_second": 3.757,
+      "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": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null