Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ad0941e19d8f3e16b529706a196d576f1dc861878473c9e0edc50ff839cc232
+oid sha256:0dd1913e6f90589df3abf8d2560fb34e47845459adaecbd301bf40a5092d3245
 size 200068512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c26c475c7e3dddeffe4e842b10dad31ff7ea78176b5573f3765b8194a0a479d2
+oid sha256:d1efa84e8fb926065944125a547e33e5e4df207e6ca626a2fa3232d9ca618b95
 size 400361770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c367127b1753877d85f6ae4547bc0da699d3dd6cb78fdd0fb4ec5a4d37b4d04a
+oid sha256:92316fc458a9640062b5fb2ade72d1167b4a6867668c1ac4b68dcb52071c6d5b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d914dc409ae93ac75985631a9974025ebaa397f621307eef226e7d6e1076a1f6
+oid sha256:babd43118aa66a4f5266d730539cf7f09611158b169d9e63dbcb83f6bbaa8626
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.056433408577878104,
+  "epoch": 0.08465011286681716,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,189 @@
       "eval_samples_per_second": 3.382,
       "eval_steps_per_second": 1.693,
       "step": 50
+    },
+    {
+      "epoch": 0.05756207674943566,
+      "grad_norm": 7.862215995788574,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 1.3288,
+      "step": 51
+    },
+    {
+      "epoch": 0.05869074492099323,
+      "grad_norm": 6.700693130493164,
+      "learning_rate": 4.6270039165317605e-05,
+      "loss": 1.3217,
+      "step": 52
+    },
+    {
+      "epoch": 0.05981941309255079,
+      "grad_norm": 8.424921035766602,
+      "learning_rate": 4.264235636489542e-05,
+      "loss": 1.4351,
+      "step": 53
+    },
+    {
+      "epoch": 0.060948081264108354,
+      "grad_norm": 8.358750343322754,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 1.9325,
+      "step": 54
+    },
+    {
+      "epoch": 0.062076749435665914,
+      "grad_norm": 8.291664123535156,
+      "learning_rate": 3.5721239031346066e-05,
+      "loss": 1.1282,
+      "step": 55
+    },
+    {
+      "epoch": 0.06320541760722348,
+      "grad_norm": 6.986010551452637,
+      "learning_rate": 3.244097923843398e-05,
+      "loss": 1.2154,
+      "step": 56
+    },
+    {
+      "epoch": 0.06433408577878104,
+      "grad_norm": 5.823822975158691,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 1.2519,
+      "step": 57
+    },
+    {
+      "epoch": 0.0654627539503386,
+      "grad_norm": 7.550477027893066,
+      "learning_rate": 2.6272266318987603e-05,
+      "loss": 1.4156,
+      "step": 58
+    },
+    {
+      "epoch": 0.06659142212189616,
+      "grad_norm": 6.91257381439209,
+      "learning_rate": 2.339555568810221e-05,
+      "loss": 1.4908,
+      "step": 59
+    },
+    {
+      "epoch": 0.06772009029345373,
+      "grad_norm": 9.72311782836914,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 1.7683,
+      "step": 60
+    },
+    {
+      "epoch": 0.06884875846501129,
+      "grad_norm": 8.531071662902832,
+      "learning_rate": 1.808479557110081e-05,
+      "loss": 1.6604,
+      "step": 61
+    },
+    {
+      "epoch": 0.06997742663656885,
+      "grad_norm": 6.506885051727295,
+      "learning_rate": 1.566085541871145e-05,
+      "loss": 1.1158,
+      "step": 62
+    },
+    {
+      "epoch": 0.07110609480812641,
+      "grad_norm": 6.313655853271484,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 1.3392,
+      "step": 63
+    },
+    {
+      "epoch": 0.07223476297968397,
+      "grad_norm": 6.619772911071777,
+      "learning_rate": 1.129891668217783e-05,
+      "loss": 1.3964,
+      "step": 64
+    },
+    {
+      "epoch": 0.07336343115124154,
+      "grad_norm": 5.63805627822876,
+      "learning_rate": 9.369221296335006e-06,
+      "loss": 0.8831,
+      "step": 65
+    },
+    {
+      "epoch": 0.0744920993227991,
+      "grad_norm": 8.772890090942383,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 1.6972,
+      "step": 66
+    },
+    {
+      "epoch": 0.07562076749435666,
+      "grad_norm": 7.003053188323975,
+      "learning_rate": 6.030737921409169e-06,
+      "loss": 1.1805,
+      "step": 67
+    },
+    {
+      "epoch": 0.07674943566591422,
+      "grad_norm": 6.298540115356445,
+      "learning_rate": 4.628304925177318e-06,
+      "loss": 1.3526,
+      "step": 68
+    },
+    {
+      "epoch": 0.07787810383747178,
+      "grad_norm": 7.14997673034668,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 1.5094,
+      "step": 69
+    },
+    {
+      "epoch": 0.07900677200902935,
+      "grad_norm": 7.56989860534668,
+      "learning_rate": 2.3703992880066638e-06,
+      "loss": 1.6164,
+      "step": 70
+    },
+    {
+      "epoch": 0.08013544018058691,
+      "grad_norm": 6.899630546569824,
+      "learning_rate": 1.5192246987791981e-06,
+      "loss": 1.2452,
+      "step": 71
+    },
+    {
+      "epoch": 0.08126410835214447,
+      "grad_norm": 6.794870853424072,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 1.6971,
+      "step": 72
+    },
+    {
+      "epoch": 0.08239277652370203,
+      "grad_norm": 6.301301956176758,
+      "learning_rate": 3.805301908254455e-07,
+      "loss": 1.5406,
+      "step": 73
+    },
+    {
+      "epoch": 0.0835214446952596,
+      "grad_norm": 6.646534442901611,
+      "learning_rate": 9.517784181422019e-08,
+      "loss": 1.4273,
+      "step": 74
+    },
+    {
+      "epoch": 0.08465011286681716,
+      "grad_norm": 6.380800724029541,
+      "learning_rate": 0.0,
+      "loss": 1.2305,
+      "step": 75
+    },
+    {
+      "epoch": 0.08465011286681716,
+      "eval_loss": 1.612352728843689,
+      "eval_runtime": 220.667,
+      "eval_samples_per_second": 3.385,
+      "eval_steps_per_second": 1.695,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -395,12 +578,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7.66894361542656e+16,
+  "total_flos": 1.150341542313984e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null