Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48521009698ee494246654415ab3c6e3b8286774f8fed7d5fe8866f47a218e35
+oid sha256:772633cd29659f5c9cf32803e150c7f641ea7e6cc65547caf8bb75904f936b71
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7006abcba83fcfb9779524148f555dd2d182d0a2272ff5b49b2bad2359939c0
+oid sha256:c6d369ff5c65ce12b205c5783709b3475b14746f107488594246c7b2925323ef
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c334162029911df951f21e152e5ddf37f5d979575a6d060ad1d369247ccd5d4
+oid sha256:c08c9f2db3519491f65c896dc5570f0688363fea4110372251c117212111fc45
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c931ece4da598a541d357f6c98f67481603252e193960022d37ddd49c584b1f
+oid sha256:a89ffc445067fef9d6d02bb3ff9e61d5e3209e6fa67c7259b3b364b90dbaa2cd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08818342151675485,
+  "epoch": 0.1763668430335097,
   "eval_steps": 9,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -206,6 +206,205 @@
       "learning_rate": 9.330127018922194e-05,
       "loss": 0.1746,
       "step": 25
+    },
+    {
+      "epoch": 0.09171075837742504,
+      "grad_norm": 6.209860801696777,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 0.4217,
+      "step": 26
+    },
+    {
+      "epoch": 0.09523809523809523,
+      "grad_norm": 3.53015398979187,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 0.5429,
+      "step": 27
+    },
+    {
+      "epoch": 0.09523809523809523,
+      "eval_loss": 0.20255467295646667,
+      "eval_runtime": 37.758,
+      "eval_samples_per_second": 6.33,
+      "eval_steps_per_second": 0.795,
+      "step": 27
+    },
+    {
+      "epoch": 0.09876543209876543,
+      "grad_norm": 5.110671520233154,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.6216,
+      "step": 28
+    },
+    {
+      "epoch": 0.10229276895943562,
+      "grad_norm": 3.3714725971221924,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 0.6694,
+      "step": 29
+    },
+    {
+      "epoch": 0.10582010582010581,
+      "grad_norm": 3.7595903873443604,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 0.501,
+      "step": 30
+    },
+    {
+      "epoch": 0.10934744268077601,
+      "grad_norm": 1.5534464120864868,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 0.4787,
+      "step": 31
+    },
+    {
+      "epoch": 0.1128747795414462,
+      "grad_norm": 2.566434383392334,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 0.4139,
+      "step": 32
+    },
+    {
+      "epoch": 0.1164021164021164,
+      "grad_norm": 1.6924530267715454,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 0.3849,
+      "step": 33
+    },
+    {
+      "epoch": 0.11992945326278659,
+      "grad_norm": 2.9056317806243896,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 0.4179,
+      "step": 34
+    },
+    {
+      "epoch": 0.12345679012345678,
+      "grad_norm": 1.0968977212905884,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 0.1236,
+      "step": 35
+    },
+    {
+      "epoch": 0.12698412698412698,
+      "grad_norm": 2.9626941680908203,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 0.1803,
+      "step": 36
+    },
+    {
+      "epoch": 0.12698412698412698,
+      "eval_loss": 0.18621611595153809,
+      "eval_runtime": 37.6672,
+      "eval_samples_per_second": 6.345,
+      "eval_steps_per_second": 0.796,
+      "step": 36
+    },
+    {
+      "epoch": 0.13051146384479717,
+      "grad_norm": 2.800790548324585,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.6245,
+      "step": 37
+    },
+    {
+      "epoch": 0.13403880070546736,
+      "grad_norm": 5.40810489654541,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 0.8681,
+      "step": 38
+    },
+    {
+      "epoch": 0.13756613756613756,
+      "grad_norm": 3.697223663330078,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 0.3298,
+      "step": 39
+    },
+    {
+      "epoch": 0.14109347442680775,
+      "grad_norm": 2.458991765975952,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.3142,
+      "step": 40
+    },
+    {
+      "epoch": 0.14462081128747795,
+      "grad_norm": 2.7322099208831787,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 0.3204,
+      "step": 41
+    },
+    {
+      "epoch": 0.14814814814814814,
+      "grad_norm": 6.406352519989014,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 0.4234,
+      "step": 42
+    },
+    {
+      "epoch": 0.15167548500881833,
+      "grad_norm": 5.081075191497803,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 0.3333,
+      "step": 43
+    },
+    {
+      "epoch": 0.15520282186948853,
+      "grad_norm": 3.3342695236206055,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 0.3729,
+      "step": 44
+    },
+    {
+      "epoch": 0.15873015873015872,
+      "grad_norm": 3.7283213138580322,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.2785,
+      "step": 45
+    },
+    {
+      "epoch": 0.15873015873015872,
+      "eval_loss": 0.11118412762880325,
+      "eval_runtime": 37.6674,
+      "eval_samples_per_second": 6.345,
+      "eval_steps_per_second": 0.796,
+      "step": 45
+    },
+    {
+      "epoch": 0.16225749559082892,
+      "grad_norm": 8.65853500366211,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.4655,
+      "step": 46
+    },
+    {
+      "epoch": 0.1657848324514991,
+      "grad_norm": 9.64456558227539,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 0.3942,
+      "step": 47
+    },
+    {
+      "epoch": 0.1693121693121693,
+      "grad_norm": 4.117836952209473,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 0.3577,
+      "step": 48
+    },
+    {
+      "epoch": 0.1728395061728395,
+      "grad_norm": 4.200088977813721,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 0.3752,
+      "step": 49
+    },
+    {
+      "epoch": 0.1763668430335097,
+      "grad_norm": 4.15980339050293,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.2969,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.173894848512e+16,
+  "total_flos": 6.347789697024e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null