Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f749725141ec6119e172ece18e17ed56c316431844fe1083e23e2a4e31e4b8f
+oid sha256:126c2c17d5d7754deb5306c028935eff2575282b32ba916854751a385ade26f4
 size 166182480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2920384a0240bd076ce4b759e9c73abf742629dea2ce0928e64d312bd82d24d5
+oid sha256:2f37344d315c540b295083b33f1e6a073b752a181e3b25d750bbcd340931a59e
 size 332574358

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bf26f00d4ba203876aa1605064144f9cda98ee0d69a8c857f477c01fb41cb42
+oid sha256:d27eaf16a875ff87481db161a11686de0ca458a0c6a5c79445fc01914c678ef0
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0dab488ab24082cad4615123be0afa77a280b889d4be61126fb6977baf9a0b0c
+oid sha256:ce04b91303855cb7b85a4c97222d5715e5c04190e466519f0ce25883cc5184cb
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa7b1343def245e4d2fff8e85db29d4c395f0dabe82c232ebe51821547b0ff6a
+oid sha256:4f5f12189c2974af3fb54681e5aee9a1f97e6d5e28e30b7263ea50c485373346
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe95ac1f3bba987f364203f4c573224702061fbd1be2889842abcd9c8f473022
+oid sha256:75ac3a1f4f929d8f1b84d220a214be57e46ab6cf1d82df8418b436e1db5000e5
 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": 0.03222168519413565,
+  "epoch": 0.0644433703882713,
   "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": 26.498,
       "eval_steps_per_second": 6.89,
       "step": 25
+    },
+    {
+      "epoch": 0.03351055260190108,
+      "grad_norm": 0.44489747285842896,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.2439,
+      "step": 26
+    },
+    {
+      "epoch": 0.03479942000966651,
+      "grad_norm": 0.4347832202911377,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.2323,
+      "step": 27
+    },
+    {
+      "epoch": 0.03608828741743193,
+      "grad_norm": 0.42812854051589966,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.2169,
+      "step": 28
+    },
+    {
+      "epoch": 0.03737715482519736,
+      "grad_norm": 0.4089065194129944,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.2039,
+      "step": 29
+    },
+    {
+      "epoch": 0.03866602223296278,
+      "grad_norm": 0.3960224688053131,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.1992,
+      "step": 30
+    },
+    {
+      "epoch": 0.03995488964072821,
+      "grad_norm": 0.4229053258895874,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.2278,
+      "step": 31
+    },
+    {
+      "epoch": 0.04124375704849364,
+      "grad_norm": 0.47951075434684753,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.2345,
+      "step": 32
+    },
+    {
+      "epoch": 0.04253262445625906,
+      "grad_norm": 0.4160752296447754,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.2111,
+      "step": 33
+    },
+    {
+      "epoch": 0.04382149186402449,
+      "grad_norm": 0.41068562865257263,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.1921,
+      "step": 34
+    },
+    {
+      "epoch": 0.04511035927178991,
+      "grad_norm": 0.3869587779045105,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.1911,
+      "step": 35
+    },
+    {
+      "epoch": 0.04639922667955534,
+      "grad_norm": 0.40918055176734924,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.2125,
+      "step": 36
+    },
+    {
+      "epoch": 0.04768809408732077,
+      "grad_norm": 0.4092864394187927,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.2247,
+      "step": 37
+    },
+    {
+      "epoch": 0.048976961495086194,
+      "grad_norm": 0.4173303544521332,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.1986,
+      "step": 38
+    },
+    {
+      "epoch": 0.05026582890285162,
+      "grad_norm": 0.42150476574897766,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.2046,
+      "step": 39
+    },
+    {
+      "epoch": 0.05155469631061704,
+      "grad_norm": 0.43464186787605286,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.2016,
+      "step": 40
+    },
+    {
+      "epoch": 0.052843563718382475,
+      "grad_norm": 0.402226060628891,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.1816,
+      "step": 41
+    },
+    {
+      "epoch": 0.0541324311261479,
+      "grad_norm": 0.3934412896633148,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.1789,
+      "step": 42
+    },
+    {
+      "epoch": 0.055421298533913324,
+      "grad_norm": 0.3596249520778656,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.1911,
+      "step": 43
+    },
+    {
+      "epoch": 0.05671016594167875,
+      "grad_norm": 0.35981810092926025,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.1667,
+      "step": 44
+    },
+    {
+      "epoch": 0.05799903334944417,
+      "grad_norm": 0.38236004114151,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.2136,
+      "step": 45
+    },
+    {
+      "epoch": 0.059287900757209605,
+      "grad_norm": 0.3796616792678833,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.2152,
+      "step": 46
+    },
+    {
+      "epoch": 0.06057676816497503,
+      "grad_norm": 0.3959929943084717,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.1892,
+      "step": 47
+    },
+    {
+      "epoch": 0.061865635572740454,
+      "grad_norm": 0.40532541275024414,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.1927,
+      "step": 48
+    },
+    {
+      "epoch": 0.06315450298050589,
+      "grad_norm": 0.40751609206199646,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.1964,
+      "step": 49
+    },
+    {
+      "epoch": 0.0644433703882713,
+      "grad_norm": 0.4269660413265228,
+      "learning_rate": 1e-05,
+      "loss": 1.2291,
+      "step": 50
+    },
+    {
+      "epoch": 0.0644433703882713,
+      "eval_loss": 1.1453883647918701,
+      "eval_runtime": 1.8866,
+      "eval_samples_per_second": 26.503,
+      "eval_steps_per_second": 6.891,
+      "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": 8.1240447254528e+16,
+  "total_flos": 1.62480894509056e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null