Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e813c2769c90e63c3e1e1d0022dc259e9e021e9d87dc6363928478522da3aa2
+oid sha256:e5f4a570afa965aac1e4b10e6e715afbe220c270be7ca5803e189d3b30457290
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfb215a01d876b5d20ad3f51a2de8db222b999d1beb0e8a5276a393eea195be9
+oid sha256:0c05738dbdb695545f24d369ab8808165d6aa7780c236424018795e6b65c0321
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:258a74b0d1a7358be05d4768f42a506876926a0bdef94a1d7d492c6d84436515
+oid sha256:3afbbeff9c2106aa6747a9a6b6d1f2974325978cb30b288d183425c5cf2062c3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f6d88d0cff0a7882c1e9d832ad0060a624f8f63df9d77d6e8619b704896e700
+oid sha256:b8eccac390378b22aeb148c260b00bec01d948946d8363d5282899af673e0e86
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02201188641866608,
+  "epoch": 0.04402377283733216,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 4.041,
       "eval_steps_per_second": 2.025,
       "step": 25
+    },
+    {
+      "epoch": 0.02289236187541272,
+      "grad_norm": 3.101707696914673,
+      "learning_rate": 0.0001848048096156426,
+      "loss": 0.6762,
+      "step": 26
+    },
+    {
+      "epoch": 0.023772837332159368,
+      "grad_norm": 4.0726189613342285,
+      "learning_rate": 0.00018290375725550417,
+      "loss": 0.4531,
+      "step": 27
+    },
+    {
+      "epoch": 0.02465331278890601,
+      "grad_norm": 7.052011013031006,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 1.0759,
+      "step": 28
+    },
+    {
+      "epoch": 0.025533788245652653,
+      "grad_norm": 1.7110868692398071,
+      "learning_rate": 0.00017880107536067218,
+      "loss": 0.4769,
+      "step": 29
+    },
+    {
+      "epoch": 0.026414263702399295,
+      "grad_norm": 2.779916763305664,
+      "learning_rate": 0.0001766044443118978,
+      "loss": 0.5725,
+      "step": 30
+    },
+    {
+      "epoch": 0.027294739159145938,
+      "grad_norm": 4.19709587097168,
+      "learning_rate": 0.00017431448254773944,
+      "loss": 0.6394,
+      "step": 31
+    },
+    {
+      "epoch": 0.02817521461589258,
+      "grad_norm": 6.238762378692627,
+      "learning_rate": 0.0001719339800338651,
+      "loss": 0.7417,
+      "step": 32
+    },
+    {
+      "epoch": 0.029055690072639227,
+      "grad_norm": 4.305187702178955,
+      "learning_rate": 0.00016946583704589973,
+      "loss": 0.754,
+      "step": 33
+    },
+    {
+      "epoch": 0.02993616552938587,
+      "grad_norm": 13.725184440612793,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 2.4752,
+      "step": 34
+    },
+    {
+      "epoch": 0.030816640986132512,
+      "grad_norm": 2.0460703372955322,
+      "learning_rate": 0.00016427876096865394,
+      "loss": 0.4011,
+      "step": 35
+    },
+    {
+      "epoch": 0.031697116442879154,
+      "grad_norm": 1.824874758720398,
+      "learning_rate": 0.0001615661475325658,
+      "loss": 0.4695,
+      "step": 36
+    },
+    {
+      "epoch": 0.0325775918996258,
+      "grad_norm": 1.9817159175872803,
+      "learning_rate": 0.00015877852522924732,
+      "loss": 0.3925,
+      "step": 37
+    },
+    {
+      "epoch": 0.03345806735637244,
+      "grad_norm": 1.2084903717041016,
+      "learning_rate": 0.0001559192903470747,
+      "loss": 0.38,
+      "step": 38
+    },
+    {
+      "epoch": 0.034338542813119086,
+      "grad_norm": 5.959559440612793,
+      "learning_rate": 0.0001529919264233205,
+      "loss": 1.468,
+      "step": 39
+    },
+    {
+      "epoch": 0.035219018269865725,
+      "grad_norm": 2.2862613201141357,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.5494,
+      "step": 40
+    },
+    {
+      "epoch": 0.03609949372661237,
+      "grad_norm": 1.3760128021240234,
+      "learning_rate": 0.00014694715627858908,
+      "loss": 0.3777,
+      "step": 41
+    },
+    {
+      "epoch": 0.03697996918335902,
+      "grad_norm": 2.4577219486236572,
+      "learning_rate": 0.00014383711467890774,
+      "loss": 0.6612,
+      "step": 42
+    },
+    {
+      "epoch": 0.037860444640105656,
+      "grad_norm": 4.882229328155518,
+      "learning_rate": 0.00014067366430758004,
+      "loss": 0.9137,
+      "step": 43
+    },
+    {
+      "epoch": 0.0387409200968523,
+      "grad_norm": 1.15999174118042,
+      "learning_rate": 0.00013746065934159123,
+      "loss": 0.2879,
+      "step": 44
+    },
+    {
+      "epoch": 0.03962139555359894,
+      "grad_norm": 3.1867716312408447,
+      "learning_rate": 0.00013420201433256689,
+      "loss": 0.7579,
+      "step": 45
+    },
+    {
+      "epoch": 0.04050187101034559,
+      "grad_norm": 3.6683099269866943,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.5053,
+      "step": 46
+    },
+    {
+      "epoch": 0.041382346467092226,
+      "grad_norm": 1.5074632167816162,
+      "learning_rate": 0.0001275637355816999,
+      "loss": 0.5215,
+      "step": 47
+    },
+    {
+      "epoch": 0.04226282192383887,
+      "grad_norm": 1.734575867652893,
+      "learning_rate": 0.00012419218955996676,
+      "loss": 0.4402,
+      "step": 48
+    },
+    {
+      "epoch": 0.04314329738058552,
+      "grad_norm": 3.334616184234619,
+      "learning_rate": 0.00012079116908177593,
+      "loss": 0.5652,
+      "step": 49
+    },
+    {
+      "epoch": 0.04402377283733216,
+      "grad_norm": 3.017249822616577,
+      "learning_rate": 0.00011736481776669306,
+      "loss": 0.5196,
+      "step": 50
+    },
+    {
+      "epoch": 0.04402377283733216,
+      "eval_loss": 0.536153256893158,
+      "eval_runtime": 118.572,
+      "eval_samples_per_second": 4.04,
+      "eval_steps_per_second": 2.024,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -217,7 +400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.29615318974464e+16,
+  "total_flos": 6.59230637948928e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null