Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76377b26eccb12c2719c6ad9b78f23f54833fde08816b13614cc7510017ace92
+oid sha256:7515ba7d08e92bfbd6854d16503623a053709f58c294e486453175c969827873
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f268107d5877f521cd3ec4eec7bfb34099d3c709a130021437eeadbe7c196fbb
+oid sha256:404251b5365082c02a3cc087a675affe245e72aa6c5ab3c40f27d7d1f12103d1
 size 335922386

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51fc24f7b2345eb5c3d017b0cbb7cf1ed8363ed52e13a11d016d7be379083a11
+oid sha256:1a9177197745203b0818e89dfcd7b5f25e7f8fce4ff58d77b34decd4ef62c3da
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d3c70f19e26d0dcf7b24cf85f026024b1a2558c7ee368e190e5685049f3fecf
+oid sha256:0bb9b57c0e059e2ac2f24fc196367f5dea169af6ea14f6c2f5a705ba299a355f
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:888396d3dfaa21ee0e4f3991c752c162af04e1714208c5cedf686e913ec5abae
+oid sha256:3502a07793e398a15ab0f70445b2e18844523fccdb6d35b94127fcb8b1957cdb
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05bfe7b469b0f11ab9ba2c80708919ab9460d27cfb1311a40874b6991943116c
+oid sha256:6c787924ec9c670fe8f2a39b10f6f6f132f67fbcf14b42940cf54999d51f4fca
 size 15024

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": 0.04024144869215292,
+  "epoch": 0.060362173038229376,
   "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": 1.5023,
       "step": 50
+    },
+    {
+      "epoch": 0.04104627766599597,
+      "grad_norm": 1.9440804719924927,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 1.3768,
+      "step": 51
+    },
+    {
+      "epoch": 0.041851106639839035,
+      "grad_norm": 1.7918343544006348,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 1.3898,
+      "step": 52
+    },
+    {
+      "epoch": 0.04265593561368209,
+      "grad_norm": 1.6904802322387695,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 1.2864,
+      "step": 53
+    },
+    {
+      "epoch": 0.04346076458752515,
+      "grad_norm": 2.007007360458374,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 1.3977,
+      "step": 54
+    },
+    {
+      "epoch": 0.04346076458752515,
+      "eval_loss": 1.397533655166626,
+      "eval_runtime": 104.7915,
+      "eval_samples_per_second": 39.927,
+      "eval_steps_per_second": 1.25,
+      "step": 54
+    },
+    {
+      "epoch": 0.04426559356136821,
+      "grad_norm": 1.9125590324401855,
+      "learning_rate": 5e-05,
+      "loss": 1.4675,
+      "step": 55
+    },
+    {
+      "epoch": 0.04507042253521127,
+      "grad_norm": 1.4900492429733276,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 1.413,
+      "step": 56
+    },
+    {
+      "epoch": 0.045875251509054325,
+      "grad_norm": 2.335010290145874,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 1.4394,
+      "step": 57
+    },
+    {
+      "epoch": 0.04668008048289739,
+      "grad_norm": 1.7225452661514282,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 1.3768,
+      "step": 58
+    },
+    {
+      "epoch": 0.04748490945674044,
+      "grad_norm": 1.1971241235733032,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 1.4439,
+      "step": 59
+    },
+    {
+      "epoch": 0.0482897384305835,
+      "grad_norm": 1.7993239164352417,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 1.4337,
+      "step": 60
+    },
+    {
+      "epoch": 0.04909456740442656,
+      "grad_norm": 1.193589448928833,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 1.2794,
+      "step": 61
+    },
+    {
+      "epoch": 0.049899396378269616,
+      "grad_norm": 1.2995184659957886,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 1.2957,
+      "step": 62
+    },
+    {
+      "epoch": 0.05070422535211268,
+      "grad_norm": 1.5458860397338867,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 1.4027,
+      "step": 63
+    },
+    {
+      "epoch": 0.05070422535211268,
+      "eval_loss": 1.3566713333129883,
+      "eval_runtime": 104.8245,
+      "eval_samples_per_second": 39.914,
+      "eval_steps_per_second": 1.25,
+      "step": 63
+    },
+    {
+      "epoch": 0.05150905432595573,
+      "grad_norm": 1.243240475654602,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.3594,
+      "step": 64
+    },
+    {
+      "epoch": 0.052313883299798795,
+      "grad_norm": 1.6665877103805542,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 1.3725,
+      "step": 65
+    },
+    {
+      "epoch": 0.05311871227364185,
+      "grad_norm": 1.9751228094100952,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 1.3449,
+      "step": 66
+    },
+    {
+      "epoch": 0.053923541247484906,
+      "grad_norm": 1.640518307685852,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 1.4013,
+      "step": 67
+    },
+    {
+      "epoch": 0.05472837022132797,
+      "grad_norm": 1.4377756118774414,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 1.3361,
+      "step": 68
+    },
+    {
+      "epoch": 0.055533199195171024,
+      "grad_norm": 1.8161500692367554,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 1.3564,
+      "step": 69
+    },
+    {
+      "epoch": 0.056338028169014086,
+      "grad_norm": 1.4024537801742554,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.5085,
+      "step": 70
+    },
+    {
+      "epoch": 0.05714285714285714,
+      "grad_norm": 1.6841168403625488,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 1.2695,
+      "step": 71
+    },
+    {
+      "epoch": 0.0579476861167002,
+      "grad_norm": 2.2560067176818848,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 1.3388,
+      "step": 72
+    },
+    {
+      "epoch": 0.0579476861167002,
+      "eval_loss": 1.3307467699050903,
+      "eval_runtime": 105.0349,
+      "eval_samples_per_second": 39.834,
+      "eval_steps_per_second": 1.247,
+      "step": 72
+    },
+    {
+      "epoch": 0.05875251509054326,
+      "grad_norm": 1.5936686992645264,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 1.2245,
+      "step": 73
+    },
+    {
+      "epoch": 0.05955734406438632,
+      "grad_norm": 1.7071914672851562,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 1.326,
+      "step": 74
+    },
+    {
+      "epoch": 0.060362173038229376,
+      "grad_norm": 1.3684706687927246,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 1.3298,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.3332355128374067e+17,
+  "total_flos": 3.564768400863396e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null