Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:828e2e541cb2d04859cf050bc78c723c432cd4b4945f138b2705b0748d4eca65
+oid sha256:70f823fa41edaf31301e81f880bbcd7ccc4788469933682fd0d660a6338f3b11
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0423ae73f4893d68ca853cdb8350e06a239ff42e868effbc64488c755dde23c
+oid sha256:53bc9ac2529c64930a85cc4234a6bad34f2a1bcc5235a9ad9b50067bc6d3c97a
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:717f303f3fed93c5d82d7c61b6a6b442bf89b64c36cf885af8203450552fafe4
+oid sha256:1a46df28312037471585ba42c2ee255b9684e3686b742e4a58dc53096d0bb825
 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": 0.010375596596804317,
+  "epoch": 0.015563394895206474,
   "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": 1.7613,
       "step": 50
+    },
+    {
+      "epoch": 0.010583108528740403,
+      "grad_norm": 1.0997047424316406,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 1.5435,
+      "step": 51
+    },
+    {
+      "epoch": 0.010790620460676489,
+      "grad_norm": 0.8529770374298096,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 1.7494,
+      "step": 52
+    },
+    {
+      "epoch": 0.010998132392612575,
+      "grad_norm": 1.1557135581970215,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 1.6652,
+      "step": 53
+    },
+    {
+      "epoch": 0.011205644324548661,
+      "grad_norm": 0.973082959651947,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 1.6062,
+      "step": 54
+    },
+    {
+      "epoch": 0.011205644324548661,
+      "eval_loss": 1.616413950920105,
+      "eval_runtime": 236.5946,
+      "eval_samples_per_second": 17.152,
+      "eval_steps_per_second": 2.147,
+      "step": 54
+    },
+    {
+      "epoch": 0.011413156256484747,
+      "grad_norm": 0.811787486076355,
+      "learning_rate": 5e-05,
+      "loss": 1.5222,
+      "step": 55
+    },
+    {
+      "epoch": 0.011620668188420833,
+      "grad_norm": 1.0629674196243286,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 1.6022,
+      "step": 56
+    },
+    {
+      "epoch": 0.011828180120356921,
+      "grad_norm": 1.2176127433776855,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 1.6937,
+      "step": 57
+    },
+    {
+      "epoch": 0.012035692052293007,
+      "grad_norm": 1.077357292175293,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 1.6371,
+      "step": 58
+    },
+    {
+      "epoch": 0.012243203984229093,
+      "grad_norm": 1.0355650186538696,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 1.6118,
+      "step": 59
+    },
+    {
+      "epoch": 0.01245071591616518,
+      "grad_norm": 1.0891892910003662,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 1.6164,
+      "step": 60
+    },
+    {
+      "epoch": 0.012658227848101266,
+      "grad_norm": 0.7828339338302612,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 1.5463,
+      "step": 61
+    },
+    {
+      "epoch": 0.012865739780037352,
+      "grad_norm": 0.8645059466362,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 1.6327,
+      "step": 62
+    },
+    {
+      "epoch": 0.013073251711973438,
+      "grad_norm": 1.0416123867034912,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 1.6092,
+      "step": 63
+    },
+    {
+      "epoch": 0.013073251711973438,
+      "eval_loss": 1.6092809438705444,
+      "eval_runtime": 236.5411,
+      "eval_samples_per_second": 17.156,
+      "eval_steps_per_second": 2.148,
+      "step": 63
+    },
+    {
+      "epoch": 0.013280763643909526,
+      "grad_norm": 1.1945778131484985,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.7276,
+      "step": 64
+    },
+    {
+      "epoch": 0.013488275575845612,
+      "grad_norm": 0.8667076230049133,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 1.6485,
+      "step": 65
+    },
+    {
+      "epoch": 0.013695787507781698,
+      "grad_norm": 0.9858114719390869,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 1.5364,
+      "step": 66
+    },
+    {
+      "epoch": 0.013903299439717784,
+      "grad_norm": 0.9003591537475586,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 1.4869,
+      "step": 67
+    },
+    {
+      "epoch": 0.01411081137165387,
+      "grad_norm": 0.9594292640686035,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 1.7525,
+      "step": 68
+    },
+    {
+      "epoch": 0.014318323303589956,
+      "grad_norm": 0.7268180847167969,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 1.59,
+      "step": 69
+    },
+    {
+      "epoch": 0.014525835235526042,
+      "grad_norm": 0.7998595833778381,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.7044,
+      "step": 70
+    },
+    {
+      "epoch": 0.014733347167462128,
+      "grad_norm": 0.9934815168380737,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 1.7302,
+      "step": 71
+    },
+    {
+      "epoch": 0.014940859099398216,
+      "grad_norm": 0.9405103921890259,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 1.5256,
+      "step": 72
+    },
+    {
+      "epoch": 0.014940859099398216,
+      "eval_loss": 1.6017986536026,
+      "eval_runtime": 236.6572,
+      "eval_samples_per_second": 17.147,
+      "eval_steps_per_second": 2.147,
+      "step": 72
+    },
+    {
+      "epoch": 0.015148371031334302,
+      "grad_norm": 0.6856156587600708,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 1.6503,
+      "step": 73
+    },
+    {
+      "epoch": 0.015355882963270388,
+      "grad_norm": 0.773373007774353,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 1.2891,
+      "step": 74
+    },
+    {
+      "epoch": 0.015563394895206474,
+      "grad_norm": 1.2244831323623657,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 1.7002,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.117474423760486e+16,
+  "total_flos": 6.120570089373696e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null