Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:924a49d12201b5ff4543c8a35fee5f664b90e9c699794b764d50ab5a616e70a6
+oid sha256:c7bbab457f4ce71dda9f00f32cf89ac4ca71dd07a0f14d7e92cef79246c5d58b
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c59fa5f015cd2bf0bef9ed20e3804334051430e46a433e3db4f2e3dc87369e5
+oid sha256:3804e2c1b2ba737fb4264dc18ff2334e44a440b781703a90aa7740d6b1fd5e12
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b43c3065d4d62ebd2fa67499eef02a708caee41e0c0226ee9fde49edb4b5c41
+oid sha256:e911014c177207add8d175713b58ac2b2f82279c0020814d4d56ddcb21a16484
 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": 0.00414524954402255,
+  "epoch": 0.0082904990880451,
   "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": 1.2871,
       "step": 25
+    },
+    {
+      "epoch": 0.004311059525783452,
+      "grad_norm": 7.218410968780518,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 1.1803,
+      "step": 26
+    },
+    {
+      "epoch": 0.004476869507544354,
+      "grad_norm": 7.529348850250244,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 1.1097,
+      "step": 27
+    },
+    {
+      "epoch": 0.004476869507544354,
+      "eval_loss": 0.4603639543056488,
+      "eval_runtime": 1575.6175,
+      "eval_samples_per_second": 3.223,
+      "eval_steps_per_second": 0.403,
+      "step": 27
+    },
+    {
+      "epoch": 0.004642679489305256,
+      "grad_norm": 3.8550705909729004,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.7259,
+      "step": 28
+    },
+    {
+      "epoch": 0.004808489471066158,
+      "grad_norm": 4.565075874328613,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 0.865,
+      "step": 29
+    },
+    {
+      "epoch": 0.00497429945282706,
+      "grad_norm": 6.3500285148620605,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 0.7888,
+      "step": 30
+    },
+    {
+      "epoch": 0.005140109434587962,
+      "grad_norm": 5.463298320770264,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 0.8169,
+      "step": 31
+    },
+    {
+      "epoch": 0.005305919416348864,
+      "grad_norm": 4.480053901672363,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 0.7127,
+      "step": 32
+    },
+    {
+      "epoch": 0.005471729398109766,
+      "grad_norm": 7.863976001739502,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 1.048,
+      "step": 33
+    },
+    {
+      "epoch": 0.005637539379870668,
+      "grad_norm": 4.669947624206543,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 0.6693,
+      "step": 34
+    },
+    {
+      "epoch": 0.00580334936163157,
+      "grad_norm": 3.4031758308410645,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 0.8024,
+      "step": 35
+    },
+    {
+      "epoch": 0.005969159343392472,
+      "grad_norm": 4.576297760009766,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 0.9314,
+      "step": 36
+    },
+    {
+      "epoch": 0.005969159343392472,
+      "eval_loss": 0.4227474331855774,
+      "eval_runtime": 1576.0515,
+      "eval_samples_per_second": 3.223,
+      "eval_steps_per_second": 0.403,
+      "step": 36
+    },
+    {
+      "epoch": 0.006134969325153374,
+      "grad_norm": 4.564301490783691,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 1.1414,
+      "step": 37
+    },
+    {
+      "epoch": 0.006300779306914276,
+      "grad_norm": 2.7618212699890137,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 0.6578,
+      "step": 38
+    },
+    {
+      "epoch": 0.006466589288675178,
+      "grad_norm": 2.4349262714385986,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 0.6903,
+      "step": 39
+    },
+    {
+      "epoch": 0.00663239927043608,
+      "grad_norm": 2.0584237575531006,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.6042,
+      "step": 40
+    },
+    {
+      "epoch": 0.006798209252196982,
+      "grad_norm": 3.166882038116455,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 0.8912,
+      "step": 41
+    },
+    {
+      "epoch": 0.006964019233957884,
+      "grad_norm": 3.8364858627319336,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 1.1009,
+      "step": 42
+    },
+    {
+      "epoch": 0.0071298292157187864,
+      "grad_norm": 3.1330361366271973,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 0.8003,
+      "step": 43
+    },
+    {
+      "epoch": 0.0072956391974796884,
+      "grad_norm": 2.2796144485473633,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 0.7073,
+      "step": 44
+    },
+    {
+      "epoch": 0.0074614491792405905,
+      "grad_norm": 2.880812406539917,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.6036,
+      "step": 45
+    },
+    {
+      "epoch": 0.0074614491792405905,
+      "eval_loss": 0.3314964473247528,
+      "eval_runtime": 1575.6793,
+      "eval_samples_per_second": 3.223,
+      "eval_steps_per_second": 0.403,
+      "step": 45
+    },
+    {
+      "epoch": 0.0076272591610014925,
+      "grad_norm": 2.4614827632904053,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.636,
+      "step": 46
+    },
+    {
+      "epoch": 0.0077930691427623945,
+      "grad_norm": 1.988437294960022,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 0.5319,
+      "step": 47
+    },
+    {
+      "epoch": 0.007958879124523296,
+      "grad_norm": 2.654332160949707,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 0.4373,
+      "step": 48
+    },
+    {
+      "epoch": 0.008124689106284198,
+      "grad_norm": 1.7638773918151855,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 0.4448,
+      "step": 49
+    },
+    {
+      "epoch": 0.0082904990880451,
+      "grad_norm": 3.3107423782348633,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.5151,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.347789697024e+16,
+  "total_flos": 1.2695579394048e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null