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:b6d0efd404390516e3b3d8c2cc3891d7ec032db67b462f924422c65bd16639d6
+oid sha256:3c5a341fbee59f5240486d695fa6eca95df46ac0769aa9791b5d430751727a5a
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fd84f74b878335578674921e6c201ddef96b386d75811ae7d090a4e0397bf3c
+oid sha256:7df5ce53c10c4d8e356da74390be3f7da78ed320ffe4f4b470586f97b7b09c41
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cda721b5035b6c32d7353550a38d047ddb776a25e42cd15a85a63cb30e818647
+oid sha256:0a537322ad8b13e53e04e7307211efb0c953aabdad90bc42ba3149fe4980cca8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6676fe28230ae15b45fb334c871c6fdf1a7984a935952b9f8650896c37a8c106
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0008767469182345824,
+  "epoch": 0.0017534938364691648,
   "eval_steps": 5,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -230,6 +230,221 @@
       "eval_samples_per_second": 9.092,
       "eval_steps_per_second": 1.137,
       "step": 25
+    },
+    {
+      "epoch": 0.0009118167949639657,
+      "grad_norm": 1.072320818901062,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 2.6271,
+      "step": 26
+    },
+    {
+      "epoch": 0.000946886671693349,
+      "grad_norm": 1.0566500425338745,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 2.5394,
+      "step": 27
+    },
+    {
+      "epoch": 0.0009819565484227323,
+      "grad_norm": 0.95279860496521,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 2.6044,
+      "step": 28
+    },
+    {
+      "epoch": 0.0010170264251521156,
+      "grad_norm": 0.9426401853561401,
+      "learning_rate": 5.392295478639225e-05,
+      "loss": 2.7527,
+      "step": 29
+    },
+    {
+      "epoch": 0.001052096301881499,
+      "grad_norm": 1.149988055229187,
+      "learning_rate": 5e-05,
+      "loss": 2.6275,
+      "step": 30
+    },
+    {
+      "epoch": 0.001052096301881499,
+      "eval_loss": 2.6402828693389893,
+      "eval_runtime": 2638.1977,
+      "eval_samples_per_second": 9.102,
+      "eval_steps_per_second": 1.138,
+      "step": 30
+    },
+    {
+      "epoch": 0.0010871661786108822,
+      "grad_norm": 1.1840800046920776,
+      "learning_rate": 4.607704521360776e-05,
+      "loss": 2.8525,
+      "step": 31
+    },
+    {
+      "epoch": 0.0011222360553402656,
+      "grad_norm": 1.0812829732894897,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 2.6406,
+      "step": 32
+    },
+    {
+      "epoch": 0.0011573059320696489,
+      "grad_norm": 0.9052231907844543,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 2.7884,
+      "step": 33
+    },
+    {
+      "epoch": 0.0011923758087990322,
+      "grad_norm": 0.9884294271469116,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 2.5666,
+      "step": 34
+    },
+    {
+      "epoch": 0.0012274456855284155,
+      "grad_norm": 1.0085114240646362,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 2.6218,
+      "step": 35
+    },
+    {
+      "epoch": 0.0012274456855284155,
+      "eval_loss": 2.630089282989502,
+      "eval_runtime": 2630.1195,
+      "eval_samples_per_second": 9.13,
+      "eval_steps_per_second": 1.141,
+      "step": 35
+    },
+    {
+      "epoch": 0.0012625155622577986,
+      "grad_norm": 0.9466912150382996,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 2.756,
+      "step": 36
+    },
+    {
+      "epoch": 0.0012975854389871819,
+      "grad_norm": 1.125657320022583,
+      "learning_rate": 2.3875071764202563e-05,
+      "loss": 2.7068,
+      "step": 37
+    },
+    {
+      "epoch": 0.0013326553157165652,
+      "grad_norm": 1.010138750076294,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 2.8166,
+      "step": 38
+    },
+    {
+      "epoch": 0.0013677251924459485,
+      "grad_norm": 0.9193635582923889,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 2.712,
+      "step": 39
+    },
+    {
+      "epoch": 0.0014027950691753318,
+      "grad_norm": 0.9951255917549133,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.6161,
+      "step": 40
+    },
+    {
+      "epoch": 0.0014027950691753318,
+      "eval_loss": 2.6228928565979004,
+      "eval_runtime": 2629.4964,
+      "eval_samples_per_second": 9.132,
+      "eval_steps_per_second": 1.142,
+      "step": 40
+    },
+    {
+      "epoch": 0.001437864945904715,
+      "grad_norm": 0.9599412679672241,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 2.496,
+      "step": 41
+    },
+    {
+      "epoch": 0.0014729348226340984,
+      "grad_norm": 0.8653432726860046,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 2.639,
+      "step": 42
+    },
+    {
+      "epoch": 0.0015080046993634817,
+      "grad_norm": 0.9962297081947327,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 2.4591,
+      "step": 43
+    },
+    {
+      "epoch": 0.001543074576092865,
+      "grad_norm": 0.9283942580223083,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 2.5208,
+      "step": 44
+    },
+    {
+      "epoch": 0.0015781444528222483,
+      "grad_norm": 1.017875075340271,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.6746,
+      "step": 45
+    },
+    {
+      "epoch": 0.0015781444528222483,
+      "eval_loss": 2.620007276535034,
+      "eval_runtime": 2637.6666,
+      "eval_samples_per_second": 9.104,
+      "eval_steps_per_second": 1.138,
+      "step": 45
+    },
+    {
+      "epoch": 0.0016132143295516316,
+      "grad_norm": 0.9226885437965393,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 2.531,
+      "step": 46
+    },
+    {
+      "epoch": 0.001648284206281015,
+      "grad_norm": 1.0046260356903076,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 2.6682,
+      "step": 47
+    },
+    {
+      "epoch": 0.0016833540830103982,
+      "grad_norm": 0.9442506432533264,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 2.4941,
+      "step": 48
+    },
+    {
+      "epoch": 0.0017184239597397815,
+      "grad_norm": 1.0019046068191528,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 2.5385,
+      "step": 49
+    },
+    {
+      "epoch": 0.0017534938364691648,
+      "grad_norm": 0.979570746421814,
+      "learning_rate": 0.0,
+      "loss": 2.6391,
+      "step": 50
+    },
+    {
+      "epoch": 0.0017534938364691648,
+      "eval_loss": 2.619568109512329,
+      "eval_runtime": 2639.7172,
+      "eval_samples_per_second": 9.097,
+      "eval_steps_per_second": 1.137,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -244,12 +459,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.85471820890112e+16,
+  "total_flos": 3.70943641780224e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null