Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2dd04fbdb4d1abcaffae7c2fc3a4b767e88fdc9584a16556c07945ed650e1d6c
+oid sha256:eb6d23cd987dc599124b98e5dd1550c704fb3641420efe4f2cd9aa28039e9a6a
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eab1ff33f5d7781ff39421e06385799603c759503050d3c79cd681340c5d9546
+oid sha256:c63cc40eee27bc9672b2f2d8a81300998c98a81612b71b9a38ce3747ce51646f
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6753a001e076e2e1251bb1d6675de25cdf726ae8d28540e03cd8d72b90cb9cfa
+oid sha256:325f7120dc876766f34a9bdbecce317e48c53594e1df312e5bdb90a8b05b39fb
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af2a2332d724dafe78dbb3b1bc6401fb5de560440a369631ae93f7d0230d2819
+oid sha256:093a84b236b3590aa51dbeb8b21831310da911f9293974944a4074f5f5c96aec
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a7cf011264d3c2208559ec2928c6c6af8f2d60f8a8f00fa15573027c4917c24
+oid sha256:4d9be1168b4110466433af88f5135351b09358d1e00ef81226f82e24f699d6aa
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ce68e78d80d41f4fc774a45d80ce4796cf7c9735338c1b30a526d2a15e115b9
+oid sha256:11587236201bf7b84ab2d9e5873b14135e64a09563cf22e3fa3fb32929065818
 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": 0.22271714922049,
+  "epoch": 0.44543429844098,
   "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": 37.159,
       "eval_steps_per_second": 9.661,
       "step": 25
+    },
+    {
+      "epoch": 0.23162583518930957,
+      "grad_norm": 0.4977087080478668,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.6454,
+      "step": 26
+    },
+    {
+      "epoch": 0.24053452115812918,
+      "grad_norm": 0.9038933515548706,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.6915,
+      "step": 27
+    },
+    {
+      "epoch": 0.24944320712694878,
+      "grad_norm": 0.9914548993110657,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 2.0145,
+      "step": 28
+    },
+    {
+      "epoch": 0.2583518930957684,
+      "grad_norm": 1.172132134437561,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.8721,
+      "step": 29
+    },
+    {
+      "epoch": 0.267260579064588,
+      "grad_norm": 0.8836953639984131,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 2.0052,
+      "step": 30
+    },
+    {
+      "epoch": 0.27616926503340755,
+      "grad_norm": 0.703058660030365,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 2.0188,
+      "step": 31
+    },
+    {
+      "epoch": 0.28507795100222716,
+      "grad_norm": 0.5177896618843079,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.974,
+      "step": 32
+    },
+    {
+      "epoch": 0.29398663697104677,
+      "grad_norm": 0.5310644507408142,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.7945,
+      "step": 33
+    },
+    {
+      "epoch": 0.3028953229398664,
+      "grad_norm": 0.8083738088607788,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.835,
+      "step": 34
+    },
+    {
+      "epoch": 0.311804008908686,
+      "grad_norm": 1.105912208557129,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.7656,
+      "step": 35
+    },
+    {
+      "epoch": 0.3207126948775056,
+      "grad_norm": 1.593446135520935,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.6878,
+      "step": 36
+    },
+    {
+      "epoch": 0.32962138084632514,
+      "grad_norm": 3.458589792251587,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.6475,
+      "step": 37
+    },
+    {
+      "epoch": 0.33853006681514475,
+      "grad_norm": 0.33230629563331604,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.6323,
+      "step": 38
+    },
+    {
+      "epoch": 0.34743875278396436,
+      "grad_norm": 0.2732144296169281,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.515,
+      "step": 39
+    },
+    {
+      "epoch": 0.35634743875278396,
+      "grad_norm": 0.32098567485809326,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.7213,
+      "step": 40
+    },
+    {
+      "epoch": 0.36525612472160357,
+      "grad_norm": 0.31850364804267883,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.8198,
+      "step": 41
+    },
+    {
+      "epoch": 0.3741648106904232,
+      "grad_norm": 0.27133655548095703,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.946,
+      "step": 42
+    },
+    {
+      "epoch": 0.3830734966592428,
+      "grad_norm": 0.29527726769447327,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.8802,
+      "step": 43
+    },
+    {
+      "epoch": 0.39198218262806234,
+      "grad_norm": 0.326080322265625,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.9288,
+      "step": 44
+    },
+    {
+      "epoch": 0.40089086859688194,
+      "grad_norm": 0.32311415672302246,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.8807,
+      "step": 45
+    },
+    {
+      "epoch": 0.40979955456570155,
+      "grad_norm": 0.37641483545303345,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.8189,
+      "step": 46
+    },
+    {
+      "epoch": 0.41870824053452116,
+      "grad_norm": 0.5488148927688599,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.7643,
+      "step": 47
+    },
+    {
+      "epoch": 0.42761692650334077,
+      "grad_norm": 0.8097848296165466,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.8119,
+      "step": 48
+    },
+    {
+      "epoch": 0.4365256124721604,
+      "grad_norm": 1.8706375360488892,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.607,
+      "step": 49
+    },
+    {
+      "epoch": 0.44543429844098,
+      "grad_norm": 4.828557968139648,
+      "learning_rate": 1e-05,
+      "loss": 2.0986,
+      "step": 50
+    },
+    {
+      "epoch": 0.44543429844098,
+      "eval_loss": 1.7255163192749023,
+      "eval_runtime": 1.3424,
+      "eval_samples_per_second": 37.246,
+      "eval_steps_per_second": 9.684,
+      "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": 5.312581507586458e+16,
+  "total_flos": 1.0620196435787776e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null