Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ca20763ebc036be3b625ea0388a65bbc8dfae7b7d3b61101a166cd1ef7aadce
+oid sha256:fdf3e944f41ec39c8768ba561bcb4da1231a8c4535ac082addfd25bd205b4a43
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50a6827982b0623b21277ba281e335e7da3dba639b6cef346da04a784a1f4ac1
+oid sha256:171981e9b45c27ddd4b1b638c14a8e3cdb3fdb2734cb82d154ac1b748c0c3de5
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c08c9f2db3519491f65c896dc5570f0688363fea4110372251c117212111fc45
+oid sha256:2ee9440c38b11df1bad9c246eb1b0880c612c59b45e12b698debf583c3696051
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a89ffc445067fef9d6d02bb3ff9e61d5e3209e6fa67c7259b3b364b90dbaa2cd
+oid sha256:f23e2214bcafb439ebc7528dcc283ef6218d509a276c0baff0743503ecbe3d92
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0037221767289510907,
+  "epoch": 0.005583265093426636,
   "eval_steps": 9,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -405,6 +405,205 @@
       "learning_rate": 5.868240888334653e-05,
       "loss": 4.4329,
       "step": 50
+    },
+    {
+      "epoch": 0.0037966202635301123,
+      "grad_norm": 3.153855323791504,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 4.5354,
+      "step": 51
+    },
+    {
+      "epoch": 0.003871063798109134,
+      "grad_norm": 2.995307683944702,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 4.5714,
+      "step": 52
+    },
+    {
+      "epoch": 0.003945507332688156,
+      "grad_norm": 2.6616311073303223,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 4.8438,
+      "step": 53
+    },
+    {
+      "epoch": 0.004019950867267178,
+      "grad_norm": 3.238128423690796,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 4.5399,
+      "step": 54
+    },
+    {
+      "epoch": 0.004019950867267178,
+      "eval_loss": 2.2302262783050537,
+      "eval_runtime": 1768.0752,
+      "eval_samples_per_second": 6.398,
+      "eval_steps_per_second": 0.8,
+      "step": 54
+    },
+    {
+      "epoch": 0.0040943944018462,
+      "grad_norm": 3.4774889945983887,
+      "learning_rate": 5e-05,
+      "loss": 4.8392,
+      "step": 55
+    },
+    {
+      "epoch": 0.004168837936425221,
+      "grad_norm": 3.0078999996185303,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 4.4709,
+      "step": 56
+    },
+    {
+      "epoch": 0.004243281471004243,
+      "grad_norm": 3.2432363033294678,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 4.637,
+      "step": 57
+    },
+    {
+      "epoch": 0.004317725005583265,
+      "grad_norm": 3.2105965614318848,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 4.5779,
+      "step": 58
+    },
+    {
+      "epoch": 0.0043921685401622865,
+      "grad_norm": 2.6800873279571533,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 4.3625,
+      "step": 59
+    },
+    {
+      "epoch": 0.004466612074741309,
+      "grad_norm": 3.262176513671875,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 4.1969,
+      "step": 60
+    },
+    {
+      "epoch": 0.004541055609320331,
+      "grad_norm": 2.9372072219848633,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 4.1523,
+      "step": 61
+    },
+    {
+      "epoch": 0.004615499143899352,
+      "grad_norm": 2.9124231338500977,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 4.5237,
+      "step": 62
+    },
+    {
+      "epoch": 0.004689942678478374,
+      "grad_norm": 2.900690793991089,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 4.2416,
+      "step": 63
+    },
+    {
+      "epoch": 0.004689942678478374,
+      "eval_loss": 2.2146337032318115,
+      "eval_runtime": 1767.3,
+      "eval_samples_per_second": 6.401,
+      "eval_steps_per_second": 0.8,
+      "step": 63
+    },
+    {
+      "epoch": 0.004764386213057396,
+      "grad_norm": 2.9719340801239014,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 4.5135,
+      "step": 64
+    },
+    {
+      "epoch": 0.004838829747636417,
+      "grad_norm": 3.173430919647217,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 4.8038,
+      "step": 65
+    },
+    {
+      "epoch": 0.0049132732822154395,
+      "grad_norm": 2.8161659240722656,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 4.1105,
+      "step": 66
+    },
+    {
+      "epoch": 0.004987716816794462,
+      "grad_norm": 3.183793067932129,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 4.8421,
+      "step": 67
+    },
+    {
+      "epoch": 0.005062160351373483,
+      "grad_norm": 2.864166498184204,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 4.2092,
+      "step": 68
+    },
+    {
+      "epoch": 0.005136603885952505,
+      "grad_norm": 2.8501057624816895,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 4.047,
+      "step": 69
+    },
+    {
+      "epoch": 0.005211047420531527,
+      "grad_norm": 2.7789459228515625,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 4.2556,
+      "step": 70
+    },
+    {
+      "epoch": 0.005285490955110548,
+      "grad_norm": 3.697779893875122,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 4.7224,
+      "step": 71
+    },
+    {
+      "epoch": 0.00535993448968957,
+      "grad_norm": 3.2184338569641113,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 4.1861,
+      "step": 72
+    },
+    {
+      "epoch": 0.00535993448968957,
+      "eval_loss": 2.202742099761963,
+      "eval_runtime": 1767.887,
+      "eval_samples_per_second": 6.399,
+      "eval_steps_per_second": 0.8,
+      "step": 72
+    },
+    {
+      "epoch": 0.0054343780242685925,
+      "grad_norm": 2.9179012775421143,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 4.5787,
+      "step": 73
+    },
+    {
+      "epoch": 0.005508821558847614,
+      "grad_norm": 2.9405431747436523,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 4.0358,
+      "step": 74
+    },
+    {
+      "epoch": 0.005583265093426636,
+      "grad_norm": 3.5514421463012695,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 4.6476,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.347789697024e+16,
+  "total_flos": 9.521684545536e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null