Training in progress, step 1, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "up_proj",
     "o_proj",
+    "q_proj",
+    "v_proj",
     "k_proj",
     "gate_proj",
-    "up_proj",
-    "q_proj",
-    "down_proj",
-    "v_proj"
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f0d81d1146cf5d68524dd39ee231533b77b2bf2f90075017bcfacbb0a66544d
+oid sha256:38d22311bae810110df98b2874b3c12c884c1d0416317bc344ec345a583acbe7
 size 48679352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70cb56dfc7deb0bfd81dd1074ca9fc4214964848421f98e17267f43a1ea1122c
+oid sha256:2d86682df81256eb3fc18f39a16289bf3ea54f835dc33ac62e1dfe2c2c892855
 size 25152500

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15bdff7b65e8869a03a6d5a3ac654b4b5584805012ac30b8ab1024abd1eb863d
+oid sha256:9034bb07100d4d5fe064a548c77d3ad73a5b37b5251e971860770351450dad98
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
+oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,102 +1,27 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04689881580490093,
-  "eval_steps": 10,
-  "global_step": 50,
+  "epoch": 5.8626097407260844e-05,
+  "eval_steps": 1,
+  "global_step": 1,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.0009379763160980185,
-      "eval_loss": 1.4842232465744019,
-      "eval_runtime": 217.4015,
-      "eval_samples_per_second": 33.036,
-      "eval_steps_per_second": 4.131,
+      "epoch": 5.8626097407260844e-05,
+      "eval_loss": 1.5188533067703247,
+      "eval_runtime": 305.6803,
+      "eval_samples_per_second": 23.495,
+      "eval_steps_per_second": 11.748,
       "step": 1
-    },
-    {
-      "epoch": 0.009379763160980185,
-      "grad_norm": 0.9162797331809998,
-      "learning_rate": 9.330127018922194e-05,
-      "loss": 1.2553,
-      "step": 10
-    },
-    {
-      "epoch": 0.009379763160980185,
-      "eval_loss": 0.9306539297103882,
-      "eval_runtime": 218.0799,
-      "eval_samples_per_second": 32.933,
-      "eval_steps_per_second": 4.118,
-      "step": 10
-    },
-    {
-      "epoch": 0.01875952632196037,
-      "grad_norm": 0.4546056091785431,
-      "learning_rate": 6.91341716182545e-05,
-      "loss": 0.848,
-      "step": 20
-    },
-    {
-      "epoch": 0.01875952632196037,
-      "eval_loss": 0.8124570250511169,
-      "eval_runtime": 217.5397,
-      "eval_samples_per_second": 33.015,
-      "eval_steps_per_second": 4.128,
-      "step": 20
-    },
-    {
-      "epoch": 0.028139289482940557,
-      "grad_norm": 0.38659822940826416,
-      "learning_rate": 3.705904774487396e-05,
-      "loss": 0.8123,
-      "step": 30
-    },
-    {
-      "epoch": 0.028139289482940557,
-      "eval_loss": 0.7834382057189941,
-      "eval_runtime": 217.551,
-      "eval_samples_per_second": 33.013,
-      "eval_steps_per_second": 4.128,
-      "step": 30
-    },
-    {
-      "epoch": 0.03751905264392074,
-      "grad_norm": 0.4110521674156189,
-      "learning_rate": 1.0332332985438248e-05,
-      "loss": 0.7568,
-      "step": 40
-    },
-    {
-      "epoch": 0.03751905264392074,
-      "eval_loss": 0.7729406356811523,
-      "eval_runtime": 218.0145,
-      "eval_samples_per_second": 32.943,
-      "eval_steps_per_second": 4.119,
-      "step": 40
-    },
-    {
-      "epoch": 0.04689881580490093,
-      "grad_norm": 0.4296030104160309,
-      "learning_rate": 0.0,
-      "loss": 0.7657,
-      "step": 50
-    },
-    {
-      "epoch": 0.04689881580490093,
-      "eval_loss": 0.770996630191803,
-      "eval_runtime": 217.8398,
-      "eval_samples_per_second": 32.969,
-      "eval_steps_per_second": 4.122,
-      "step": 50
     }
   ],
-  "logging_steps": 10,
-  "max_steps": 50,
+  "logging_steps": 5,
+  "max_steps": 1,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
-  "save_steps": 13,
+  "save_steps": 1,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -109,8 +34,8 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.5657843654656e+16,
-  "train_batch_size": 8,
+  "total_flos": 69572304568320.0,
+  "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null
 }

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9a998c94defdb184f2f299f024c45fdde5b94d648dd88b9a66f92a152cd06e5
+oid sha256:ccd44bccb49a39b016b806d1e38b44974d91445f6450d8769e0df2d1dbbce2ab
 size 6776